build-feature
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon user-supplied feature requirements and project plans. This ingestion of untrusted external data creates a surface where malicious instructions could be embedded to influence the agent's behavior during the build process.
- Ingestion points: Feature definitions and plan approval inputs referenced in the
build-featurelogic and::ACTIVATEblock. - Boundary markers: The instructions do not define specific delimiters (e.g., XML tags or triple quotes) to separate user data from the agent's core instructions.
- Capability inventory: The skill instructions imply subsequent code generation, file modification, and status reporting based on the ingested requirements.
- Sanitization: There are no explicit instructions for the agent to sanitize, validate, or ignore control sequences within the feature descriptions.
Audit Metadata