pm-initiate-problem-framing
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional steps for analyzing project data and generating a structured report. No malicious code, obfuscation, or dangerous operations were detected.
- [PROMPT_INJECTION]: The skill is designed to ingest and summarize external data from project files and feedback reports, which constitutes a potential surface for indirect prompt injection. This risk is effectively mitigated by the skill's lack of executable capabilities.
- Ingestion points: Reads project artifacts including kickoff notes, plans, tracker data, and user feedback (SKILL.md, Step 2).
- Boundary markers: No explicit delimiters are used to separate ingested untrusted content from the system prompt.
- Capability inventory: The skill contains no instructions for network exfiltration, file system modification, or shell command execution.
- Sanitization: No sanitization or validation of external data is performed before processing.
Audit Metadata