pm-feedback
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user feedback gathered from external sources, creating a surface for indirect instructions to influence the agent.
- Ingestion points: Untrusted data is ingested through the Read tool, AskUserQuestion tool, and exa web search tools.
- Boundary markers: The skill does not implement delimiters or safety instructions to isolate external content.
- Capability inventory: The agent has access to shell execution via the Bash tool, file writing via the Write tool, and the ability to spawn sub-agents.
- Sanitization: Input data is not sanitized or filtered before being processed by analysis sub-agents.
- [COMMAND_EXECUTION]: The preamble section uses the Bash tool to execute a local check-update.sh script for version verification.
Audit Metadata