flake
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform various operations including viewing PRs, reading issue content, fetching job logs, and rerunning Actions jobs. These operations are scoped to theremotion-dev/remotionrepository, which is consistent with the skill's stated purpose and the author's identity. - [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from GitHub Actions logs and external issue bodies to extract failure signatures. This creates a surface for indirect prompt injection if an attacker can control log output. However, the risk is minimized by specific instructions to strip variable elements (timestamps, paths, random IDs) and the requirement to follow a rigid Markdown table format.
- Ingestion points: The skill ingests data from Actions logs (
gh api ... logs) and issue content (gh issue view). - Boundary markers: No explicit boundary markers are used when the agent processes the retrieved data.
- Capability inventory: The skill allows the agent to write to GitHub issues and trigger workflow reruns.
- Sanitization: The instructions explicitly require the agent to sanitize the extracted failure signature by removing dynamic content like timestamps and ANSI codes.
Audit Metadata