lgnh-brain-query
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify the use of the
grepcommand to perform keyword searches across files within thewiki/subdirectory of the knowledge base. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses the local file system at
/Users/loegnah/note/brain. This access is restricted to the local environment and aligns with the author's defined context. No network exfiltration or hardcoded credentials were detected. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads external data from
index.md, files within thewiki/directory, and therefs/directory. - Boundary markers: The instructions do not specify any boundary markers or delimiters for the data ingested from these files.
- Capability inventory: The skill possesses the ability to read local files and write results to the
wiki/analyses/folder andlog.mdfile. - Sanitization: There is no evidence of sanitization or validation of the content read from the wiki files before it is processed by the agent.
Audit Metadata