github-actions
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates an attack surface for indirect prompt injection as it ingests logs from external GitHub Actions runs.
- Ingestion points: The skill uses
gh run view --log-failedand run URLs to fetch log data from external sources into the agent's context (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions to disregard potentially malicious commands embedded within the logs.
- Capability inventory: The agent is tasked with classifying failures and suggesting or performing edits to
.github/workflowsand project code (SKILL.md). - Sanitization: No sanitization or filtering of the fetched log content is mentioned before the agent processes it.
Audit Metadata