actions-manager
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The agent processes external data from GitHub Actions logs and artifacts which could serve as a vector for indirect prompt injection.
- Ingestion points: The agent reads log output and artifact details from the GitHub REST API as specified in the SKILL.md core capabilities.
- Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions found within the logs.
- Capability inventory: The agent has the ability to trigger workflow runs, cancel runs, and enable or disable workflows via the GitHub REST API.
- Sanitization: No sanitization or validation logic is specified for handling the ingested log content.
- [NO_CODE]: The skill is composed entirely of markdown instructions and YAML configuration files. It does not include any scripts or executable files that could run on the host system.
Audit Metadata