lov-skill-pricing

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted external data including skill source code, README files, and capability briefs, which presents a surface for instructions embedded in data to influence agent behavior.
  • Ingestion points: Workflow Step 1 in SKILL.md and the Usage section in README.md specify that the skill ingests source directories, manifest files, and capacity briefs for evaluation.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands within the ingested data.
  • Capability inventory: The skill utilizes a local utility script (scripts/validate_skill.py) that performs extensive file reading to check for metadata validity and hygiene issues like hardcoded paths; however, no network access or arbitrary code execution capabilities are present.
  • Sanitization: There is no mention of sanitizing or filtering the content of the analyzed files before processing them in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:58 AM
Security Audit — agent-trust-hub — lov-skill-pricing