turtleneck-stress
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external design descriptions and repository layouts which may contain untrusted content.\n
- Ingestion points: Processes user-provided design descriptions, diagrams, repo layouts, and documents (SKILL.md).\n
- Boundary markers: Absent. The instructions do not provide delimiters or directives to ignore instructions embedded in the input designs.\n
- Capability inventory: The skill frontmatter does not list any allowed-tools, limiting the agent to internal text processing and response generation.\n
- Sanitization: Absent. There is no mention of filtering or validating the ingested content.\n- [SAFE]: The skill uses local relative references to its own project documentation for procedures and vocabulary, which is consistent with its stated purpose. No network operations, sensitive file access, or command execution patterns were identified.
Audit Metadata