wiki-audit
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes content from wiki pages through the skillwiki audit command, which represents an attack surface for indirect prompt injection.\n
- Ingestion points: Content is ingested from wiki pages via the skillwiki audit tool in Step 1 of SKILL.md.\n
- Boundary markers: The instructions lack explicit boundary markers or directions for the agent to ignore instructions embedded within the audited content.\n
- Capability inventory: The skill has the capability to execute the skillwiki CLI and write to log.md as described in Step 3.\n
- Sanitization: There is no evidence of sanitization for the content read from the wiki pages.\n- [COMMAND_EXECUTION]: The skill uses a command-line tool skillwiki to perform vault resolution and page auditing.\n
- Evidence: The skill instructions explicitly call skillwiki path, skillwiki lang, and skillwiki audit .
Audit Metadata