proof-assistant

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data which could potentially contain hidden instructions.
  • Ingestion points: Untrusted data enters the agent context through the algorithm, code, claim, and partialProof fields defined in the input schema of SKILL.md.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instructions" markers to isolate user-provided code and claims from the agent's logic.
  • Capability inventory: The skill is configured with Read, Write, Grep, and Glob tools in its allowed-tools frontmatter, allowing it to interact with the file system.
  • Sanitization: No input validation or sanitization mechanisms are defined to filter or escape instructions embedded within the provided algorithm or code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 08:23 PM