pigdoc
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill initiates network requests to search.pig4cloud.com to retrieve documentation hits. This is the primary function of the skill and targets the official domain for the PIG framework.
- [COMMAND_EXECUTION]: The skill documentation provides a curl command template for interacting with the search API. This command is used to fetch external data which is then processed by the agent.
- [PROMPT_INJECTION]: The skill ingests untrusted data from an external source (the hits[].content field from the PIG search API) and incorporates it into its summary and response. While the source is the official documentation portal, the lack of explicit boundary markers or sanitization for this external content creates a surface for indirect prompt injection.
Audit Metadata