awiki-page
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill enables the agent to execute shell commands using the
awiki-clitool to perform mutations on remote page data and slugs. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the context when the agent reads markdown content from local files (e.g., via the
--markdown-fileparameter) or processes inline strings. - Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to prevent the agent from following instructions embedded within the ingested markdown content.
- Capability inventory: The agent can execute bash commands through a restricted tool and read local file system content.
- Sanitization: There is no evidence of validation, escaping, or filtering of the markdown content before it is passed to the execution tool.
Audit Metadata