bias-check
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied documents and plans, which could contain hidden instructions aimed at influencing the agent's behavior during analysis.\n
- Ingestion points: The skill accepts a 'decision, plan, or document to check' as its primary input in SKILL.md.\n
- Boundary markers: The instructions do not prescribe the use of delimiters or 'ignore' instructions when the agent processes the external text.\n
- Capability inventory: The skill's capabilities are limited to searching local file paths (e.g.,
{Product}/Product/decisions/) and generating text output. It lacks high-risk capabilities like network access or arbitrary command execution.\n - Sanitization: There is no requirement for the agent to sanitize or validate the input text for malicious patterns before analysis.\n- [NO_CODE]: The skill does not contain any executable scripts, binaries, or logic that would trigger code execution. It relies entirely on natural language instructions for the agent.
Audit Metadata