pstack-correct
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to analyze external data such as commit messages, reverts, and review comments to identify recurring patterns of mistakes.\n
- Ingestion points: Processes repository history and developer feedback as described in
SKILL.md.\n - Boundary markers: No specific delimiters are defined to separate instruction content from the historical data being analyzed.\n
- Capability inventory: The agent is empowered to modify repository architecture, add linting rules, and execute shell commands to verify fixes.\n
- Sanitization: There is no mention of sanitizing or filtering input from commit messages or comments.\n- [COMMAND_EXECUTION]: The instructions direct the agent to run commands locally and in CI to prove that new checks fail on past mistakes and pass on current code.\n- [EXTERNAL_DOWNLOADS]:
UPSTREAM.mdcontains references to the skill's origin in a public GitHub repository. These are provided for tracking and attribution purposes and do not trigger unauthorized downloads or execution of remote content.
Audit Metadata