product-manager-agent
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to gather and analyze evidence from potentially untrusted external sources, including market research, application logs, and user tickets.
- Ingestion points: The agent reads external research URLs, logs, tickets, and analytics artifacts to populate
research.mdandevidence-log.md. - Capability inventory: The skill has the capability to write files to the repository (
docs/product-manager/) and mentions delivery of results via email or Telegram if tools are available. - Boundary markers: Absent. There are no explicit instructions or delimiters provided to prevent the agent from following instructions embedded within the ingested research or ticket data.
- Sanitization: Absent. The skill does not define methods for sanitizing or escaping content retrieved during the ResearchPhase.
Audit Metadata