stats-sanity
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from manuscripts and reports, which introduces an attack surface where embedded instructions could attempt to influence the agent's behavior.
- Ingestion points: Reported metrics, denominators, and result tables from external manuscripts and reports (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat external content as data only or to ignore natural language instructions embedded within the processed text.
- Capability inventory: The instructions direct the agent to recompute statistics using code or calculators, which provides a capability that could be targeted by malicious data-resident payloads.
- Sanitization: The skill does not define any sanitization, filtering, or validation steps for the content extracted from external sources.
Audit Metadata