actions-debugger
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- PROMPT_INJECTION (LOW): Indirect Prompt Injection vulnerability.
- Ingestion points: The skill ingests untrusted data from GitHub Action logs via the
gh run viewcommand. - Boundary markers: Absent; there are no instructions provided to the agent to treat log content as untrusted or to ignore embedded commands.
- Capability inventory: The skill allows the agent to execute Bash commands through the GitHub CLI (
gh:*), providing a surface for an attacker to potentially trigger unauthorized GitHub API actions. - Sanitization: Absent; log output is passed directly to the agent's context through standard shell pipes.
- COMMAND_EXECUTION (SAFE): The skill uses the legitimate
ghCLI,sed, andtailtools as intended for its primary purpose.
Audit Metadata