update-knowledge-base
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from untrusted external sources, which could contain malicious instructions meant to influence the agent's behavior.
- Ingestion points: The skill reads recent shipped work from external ticket sources (e.g., Linear, Jira, GitHub Issues) and fetches documentation from user-provided URLs (Help Center and Changelog).
- Boundary markers: The prompt template does not include delimiters or specific instructions for the agent to ignore any embedded commands or instructions found within the tickets or web pages.
- Capability inventory: The agent utilizes tool access for issue trackers (Linear/Jira/GitHub), web browsing, and file writing to Google Drive.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the external content before it is processed by the agent.
Audit Metadata