excavate-assumptions
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied claims or framings, creating an ingestion point for untrusted data.
- Ingestion points: The agent is instructed to analyze the 'current framing' in SKILL.md.
- Boundary markers: No explicit delimiters are used to separate user data from instructions.
- Capability inventory: The skill body consists of natural language instructions only and does not list any allowed-tools or perform file/network operations.
- Sanitization: No input sanitization is present.
- [NO_CODE]: The skill is entirely composed of Markdown text and YAML metadata. There are no associated scripts, binaries, or complex configurations that could execute malicious logic.
Audit Metadata