re-fp-runtime
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing necessary toolchains (GHC, OCaml) from official and well-known package managers such as apt, brew, ghcup, and opam, which are recognized as trusted services.\n- [INDIRECT_PROMPT_INJECTION]: As a reverse engineering tool, this skill processes untrusted binary files which represents an inherent attack surface for indirect prompt injection.\n
- Ingestion points: External binary files processed as 'sample' in SKILL.md through tools like readelf and file.\n
- Boundary markers: The instructions do not define specific delimiters for separating untrusted binary data from the agent's reasoning instructions.\n
- Capability inventory: Employs standard utilities like readelf, nm, and xxd to parse file content.\n
- Sanitization: The skill relies on the agent's interpretation of tool output without explicit sanitization steps for the binary content.
Audit Metadata