fix-ci
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources including GitHub Action logs and external check links which may contain untrusted content.
- Ingestion points: GitHub Action logs retrieved via
ghCLI and content from external check links described in the workflow. - Boundary markers: The instructions lack specific delimiters or instructions to the agent to disregard potential instructions embedded within the CI logs or external sites.
- Capability inventory: The workflow implies the agent has the ability to modify source code and execute git commands (
Push), which are standard for developer tools but represent a capability surface if the agent is influenced by malicious log output. - Sanitization: There is no evidence of filtering or sanitization of the log content before it is processed by the agent.
Audit Metadata