compliance-anthropic
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from external sources such as Data Processing Agreements (DPAs) and Data Subject Requests (DSRs). \n
- Ingestion points: Instructions in SKILL.md direct the agent to review DPAs and handle data subject requests. \n
- Boundary markers: The skill does not provide specific instructions to the agent to use delimiters or to ignore instructions that might be embedded in these external documents. \n
- Capability inventory: The skill does not have access to tools for network operations, file system writes, or command execution, neutralizing the risk of exploitation. \n
- Sanitization: No sanitization or filtering of input content is specified. \n- [NO_CODE]: The skill consists entirely of markdown instructions and license text, with no executable scripts, binaries, or automated tasks.
Audit Metadata