pm-requirements-generator
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and associated stack profiles do not contain any detected malicious patterns, obfuscation, or unauthorized network operations. The use of local filesystem paths and references to vendor-specific harness components aligns with the skill's stated purpose of project documentation management.
- [PROMPT_INJECTION]: The skill ingests untrusted data from external sources to generate its output, creating a surface for indirect prompt injection.
- Ingestion points: The agent reads scope descriptions from chat and design-brief.md files from the filesystem.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the ingested data.
- Capability inventory: The skill is designed to write documentation to the local filesystem in the docs/versions directory.
- Sanitization: The instructions do not specify any validation, filtering, or sanitization logic for the ingested content.
Audit Metadata