argo-local-search
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external web sources and local files which are untrusted.
- Ingestion points: Untrusted data enters the agent context through the
argo searchtool and theseek.pyscript which aggregate web and local content. - Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from executing commands that might be embedded in the retrieved search results.
- Capability inventory: The skill uses the
argoCLI and a Python script (seek.py) to process data and return it to the agent, specifically using flags like--fields agentintended for model ingestion. - Sanitization: There is no evidence of content sanitization or validation performed on the retrieved data before it is presented to the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with search utilities.
- Evidence:
SKILL.mdcontains examples for executingargo searchandpython3 sub-skills/local-seek/scripts/seek.pyto perform its primary function.
Audit Metadata