wiki-lint

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill reads and evaluates content from all wiki pages and the sources/ directory, which creates a surface for indirect prompt injection. Adversarial instructions within these files could attempt to influence the agent's logic during the linting process.
  • Ingestion points: All pages in the wiki and files within the sources/ directory.
  • Boundary markers: There are no instructions or delimiters provided to the agent to ignore instructions embedded within the processed data.
  • Capability inventory: The skill utilizes file system read access and writes findings to the system/lint-report.md file.
  • Sanitization: No sanitization, validation, or escaping of the ingested content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 07:02 PM