spec
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files, which could contain malicious instructions aimed at overriding the agent's behavior.
- Ingestion points: The skill reads user-supplied or discovered scope files (
docs/scope-*.md) and repository content including instructions, architecture decisions, code, and tests as described in sections 1 and 3. - Boundary markers: There are no defined delimiters or instructions to treat ingested content as passive data, which could allow instructions within those files to influence the output or behavior.
- Capability inventory: The skill is capable of reading repository files and writing output to the local file system (
docs/spec-*.md). - Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the content extracted from external files before using it to generate specifications.
Audit Metadata