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.mdfile. - Sanitization: No sanitization, validation, or escaping of the ingested content is specified.
Audit Metadata