signals-scout-data-pipelines
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external pipeline logs and execution traces (e.g., via
cdp-functions-logs-retrieve). This creates a vulnerability surface where malicious instructions embedded in log data or error messages from external services could influence the agent's reasoning or reporting behavior. While the instructions include a 'Data Hygiene' section to treat inputs as untrusted, static analysis cannot guarantee runtime safety against adversarial data. Severity is rated LOW as this is a structural vulnerability typical of monitoring skills.
Audit Metadata