aris-proof-writer

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed of natural language instructions and does not contain any code, scripts, or binary payloads.\n- [SAFE]: No evidence of obfuscation, hardcoded credentials, or persistence mechanisms was found in the skill content or metadata.\n- [SAFE]: The skill utilizes allowed file system tools (Read, Write, Edit, Grep, Glob) for its intended purpose and does not request network access or elevated privileges.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes external mathematical content without explicit sanitization or boundary markers. 1. Ingestion points: Theorem statements, assumptions, and proof sketches provided in arguments or read from local files during the Gather Proof Context step. 2. Boundary markers: No delimiters or protective framing are used for ingested content. 3. Capability inventory: The skill uses Read, Write, Edit, Grep, and Glob tools to manage local files. 4. Sanitization: No validation or filtering is applied to the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 01:42 AM
Security Audit — agent-trust-hub — aris-proof-writer