pstack
Use pstack with claude, codex, pi - Skills and principles for rigorous AI-assisted engineering
No outside reports on file
Use pstack only with non-sensitive code and error logs; never feed it production errors containing secrets, and verify that your AI agent doesn't accidentally leak stack trace contents in responses.
Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (backnotprop/pstack)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/backnotprop/pstack ↗
About Pstack
pstack is a skill (add-on tool) for AI coding agents like Claude that appears to help with stack trace analysis and debugging. It lets AI agents inspect and understand error messages from code execution more effectively.
Who it’s for
Developers using AI coding assistants who want their AI helpers to better understand and debug code errors. Teams that use Claude or similar agents for code generation and troubleshooting.
Alternatives
- Built-in Claude error analysis: Claude can often understand errors without a separate skill
- GitHub Copilot error hints: VS Code's native debugging features paired with Copilot
- OpenAI function calling for debugging: Custom tools that safely wrap your own error handlers
- Traditional debugging tools:
gdb,lldb, or language-specific debuggers give you full control
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README. The GitHub repository link is provided, but setup steps vary by which agent you're using (Claude Desktop, VS Code extension, etc.).
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 3.1k
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-28).
Risks to watch for
- Exposure of sensitive errors: Stack traces can leak private API keys, database names, file paths, or business logic if your AI agent processes real production errors
- Malicious error injection: An attacker could craft fake error messages in logs or test files that trick the AI into unsafe recommendations
- Data in memory dumps: If the skill accesses full stack dumps, it might capture secrets or personal data from memory
- Supply chain risk: The project is a community mirror; it depends on the original cursor/plugins repository, which could change without notice
- No verified safety claims: The project has moderate GitHub stars but minimal npm usage signals, making real-world safety data unclear
How to lower the risk
Least-privilege permissions
- Run the AI agent in a sandboxed environment with no access to live databases
- Limit which log files or error messages the agent can analyze
Network isolation
- Prevent the agent from sending stack traces or error details to external services
- Keep the skill offline or behind a firewall in sensitive environments
Monitoring
- Log what errors the AI agent processes and what recommendations it makes
- Review outputs before the agent acts on debugging suggestions
Red flags to watch for
- Agent recommending changes based on production secrets in stack traces
- Errors appearing in logs that don't match your actual code
- Agent suggesting to disable security checks after analyzing errors
Questions
How do I install Pstack?
Pstack does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/backnotprop/pstack.
Are there security reports about Pstack?
No reports found for this package in our research (last checked 2026-10-28). Pstack currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include exposure of sensitive errors, malicious error injection, data in memory dumps.
Is Pstack actively maintained?
Pstack has 3.1k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/backnotprop/pstack before pinning it in production.
What are alternatives to Pstack?
Notable alternatives to Pstack include Built-in Claude error analysis (Claude can often understand errors without a separate skill), GitHub Copilot error hints (VS Code's native debugging features paired with Copilot), OpenAI function calling for debugging (Custom tools that review wrap your own error handlers), Traditional debugging tools (`gdb`, `lldb`, or language-specific debuggers give you full control). You can also compare Pstack side by side with other skills in the Related tools section on this page.
README badge and team notes
Maintain or use Pstack? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/backnotprop-pstack)HTML embed:
<a href="https://agentarmorhq.com/skills/backnotprop-pstack"><img src="https://agentarmorhq.com/api/badge/backnotprop-pstack" alt="AgentArmorHQ Risk Grade for Pstack" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "backnotprop-pstack"Share with your security lead
Need sign-off to use pstack? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: pstack
- **Listing URL:** https://agentarmorhq.com/skills/backnotprop-pstack
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 3.1k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (backnotprop/pstack)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/backnotprop/pstack
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 25, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- AI agent skill
- Publisher
- backnotprop
- Source code
- github.com/backnotprop/pstack
- Est. context load
- ~50 tokens idle · ~450 tokens when active (on-demand skill)
- Popularity
- 3.1k GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-25
Community
Discussions for Pstack
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude