python-pep8-coach
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Python source code, which represents an untrusted data ingestion surface.
- Ingestion points: Content of scanned Python files and folder structures (SKILL.md).
- Boundary markers: The instructions explicitly direct the agent to treat the contents of scanned files as untrusted data and limit analysis strictly to formatting rules (SKILL.md).
- Capability inventory: File system read access for linting and write access for formatting via
flake8andblack. - Sanitization: The skill mandates path quoting and validation for all command-line operations to mitigate risks.
- [COMMAND_EXECUTION]: The skill invokes command-line tools (
flake8,black) to analyze and format code. It includes a specific security rule to sanitize and quote target paths to prevent command injection vulnerabilities. - [EXTERNAL_DOWNLOADS]: The skill follows secure practices for dependency management by refusing to automatically install missing packages. Instead, it prompts the user with the necessary commands for manual installation, preventing unauthorized supply-chain interactions.
Audit Metadata