open-targets-search
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The documentation instructs the agent to use the
findcommand to locate the script path within the local file system and execute thescripts/searchbash wrapper. - [DATA_EXFILTRATION]: The skill communicates with an external API at
api.valyu.ai. While this is the primary functionality of the skill, it involves sending user queries and an API key to a non-whitelisted third-party domain. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it retrieves and processes unstructured content from external search results.
- Ingestion points: The
results[].contentandresults[].titlefields from the Valyu API response are ingested into the agent context. - Boundary markers: No delimiters or protective instructions are specified to prevent the agent from following commands embedded in the search results.
- Capability inventory: The agent has the capability to execute local scripts (
scripts/search) and make network calls viafetch. - Sanitization: There is no evidence of sanitization or validation of the content returned from the external API.
Audit Metadata