to-spec
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external repository files and documentation to synthesize implementation specs, creating a surface where malicious content in those files could influence agent behavior or output.
- Ingestion points: The skill reads
CONTEXT.md,docs/glossary.md,docs/decisions/, and the repository codebase. - Boundary markers: The instructions lack explicit delimiters or safety markers to isolate ingested content from agent instructions.
- Capability inventory: The skill has capabilities to write files to the
docs/specs/directory and publish content to an external project tracker. - Sanitization: The process does not define any sanitization or validation steps for data extracted from the repository before it is used in the specification template.
Audit Metadata