gsd-new-project
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied 'idea documents' (referenced via the
--autoflag) to generate requirements and roadmaps. This ingestion of external, untrusted content presents a risk where instructions embedded in the document could attempt to override agent behavior. - Ingestion points: The skill explicitly expects an 'idea document via @ reference' to drive the automated workflow defined in
SKILL.md. - Boundary markers: The manifest does not define specific delimiters or instructions for the agent to ignore potentially malicious commands within the ingested data.
- Capability inventory: The skill utilizes
Bash,Write,Read, andAgenttools to create and manage the.planning/directory structure. - Sanitization: No input validation or content filtering mechanisms are specified for the processed idea documents.
Audit Metadata