test-naming-enforcer
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill structure presents a potential surface for indirect prompt injection due to the combination of keyword-based triggers and broad tool access.
- Ingestion points: Processes user requests triggered by keywords such as "test", "test enforcer", or "test naming enforcer" as defined in SKILL.md.
- Boundary markers: The instructions in SKILL.md do not include explicit delimiters or instructions to ignore potentially malicious embedded commands in user input.
- Capability inventory: The skill is configured to use Read, Write, Edit, Bash(cmd:*), and Grep tools.
- Sanitization: There are no provided mechanisms for input validation or content filtering to prevent the interpolation of malicious instructions into the agent's logic.
Audit Metadata