broll-render

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides operational guidelines for inspecting legacy HyperFrames records in a read-only capacity. It explicitly prohibits running rendering software, opening previews, or writing delivery artifacts, which limits the potential for unauthorized actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from legacy render records and JSON files such as composition-identity.json. While this constitutes a potential attack surface, the risk is negligible due to the skill's restricted verification purpose and the absence of executable capabilities.
  • Ingestion points: composition-identity.json and legacy render record files (SKILL.md).
  • Boundary markers: Absent; the instructions do not require the use of delimiters when processing records.
  • Capability inventory: Limited to file reading, hash verification, and metadata comparison (SKILL.md).
  • Sanitization: None specified; the skill performs verification based on content hashes and metadata equality (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:43 AM
Security Audit — agent-trust-hub — broll-render