pre-mortem
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external product requirements documents (PRDs) or product plans provided by the user. This data is untrusted and could contain malicious instructions intended to manipulate the agent's analysis or its use of available tools (like web search and file writing).
- Ingestion points: Product Requirements Documents (PRD) or product plan files provided by the user as described in the Instructions section of
SKILL.md. - Boundary markers: None; the instructions do not suggest wrapping the external content in delimiters or providing instructions to ignore embedded commands.
- Capability inventory: The skill performs file reading, web searching for competitive research, and file writing to save the output markdown document.
- Sanitization: None; the agent is instructed to read the content thoroughly without any filtering or validation steps.
- [PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable directly within its purpose statement. User-supplied input passed through this variable could attempt to override the primary instructions or the defined persona of a veteran product manager.
Audit Metadata