ops-investigate-alert
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources such as monitoring logs, traces, and alert descriptions which are potentially attacker-controlled.
- Ingestion points: The skill ingests data from external monitoring MCP servers (metrics, logs, traces) and the GitHub API via the
ghCLI (tags, commit messages). - Boundary markers: There are no explicit instructions to the agent to treat fetched logs or alert descriptions as untrusted data or to ignore any instructions embedded within them.
- Capability inventory: The skill utilizes the
Bashtool, providing a path for command execution if the agent is misled by injected instructions. - Sanitization: No sanitization, filtering, or validation is performed on the content of logs or alert metadata before it is added to the agent's context.
Audit Metadata