skill-validator

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No security issues were identified in the skill instructions or YAML configuration. The skill is designed for local metadata validation and documentation checks, following the principle of least privilege by requesting only read access to target directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it ingests untrusted data from the filesystem during the validation process. However, the risk is mitigated as the skill lacks sensitive capabilities such as network access, system command execution, or file write permissions.
  • Ingestion points: Files (YAML/Markdown) within the user-provided skill_directory path referenced in SKILL.md.
  • Boundary markers: Not present; the instructions do not specify delimiters or markers to differentiate between instructions and untrusted data.
  • Capability inventory: No subprocess calls, network operations, or file-write operations are defined in the skill files.
  • Sanitization: No validation or escaping of the ingested file content is mentioned beyond structural YAML parsing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:51 PM