search-jay-llm-wiki

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to utilize the rg (ripgrep) command-line utility for searching the local filesystem when other transport methods are unavailable (SKILL.md).
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing data from an external local repository.
  • Ingestion points: Files located under E:\Code\Personal\jay-llm-wiki are read and processed (SKILL.md).
  • Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded instructions within the wiki content.
  • Capability inventory: The skill allows for local file system reads and the execution of shell commands via the rg utility (SKILL.md).
  • Sanitization: Absent; while the skill specifies that sensitive values should be removed from search terms, there is no validation or sanitization applied to the content retrieved from the wiki files themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 09:18 AM
Security Audit — agent-trust-hub — search-jay-llm-wiki