pencil-mcp-get-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves external design specifications via the
get_guidelinestool and instructs the agent to apply these rules to future design actions. This creates an attack surface where instructions embedded in the retrieved content could potentially influence the agent's behavior. - Ingestion points: Data enters the agent's context through the output of the
get_guidelinestool (SKILL.md). - Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded within the guideline data.
- Capability inventory: The skill indicates that the retrieved information will be used to guide subsequent
batch_designtool calls. - Sanitization: There is no evidence of sanitization, filtering, or validation of the guideline content before it is processed by the agent.
Audit Metadata