create-strategy
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's operations are confined to reading project documentation and generating text based on that context.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it ingests project documentation and interpolates it into an agent prompt without delimiters. This is considered safe as it is the primary intended functionality of the skill.\n
- Ingestion points: Requirements, architecture documents, and test plans read from the project directory.\n
- Boundary markers: None explicitly used when passing context to the test-strategist agent.\n
- Capability inventory: Read, Write, Glob, Grep, Skill, Task.\n
- Sanitization: No sanitization is performed on the ingested documentation.
Audit Metadata