self-test

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script (tests/run-all.sh) and the gh-manager binary to perform automated testing. This functionality is essential for the skill's stated purpose of self-test and validation.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted data from GitHub, such as issue descriptions and pull request comments, which could contain adversarial instructions.\n
  • Ingestion points: Data is retrieved from GitHub via API calls initiated by the gh-manager tool.\n
  • Boundary markers: The skill does not provide instructions for the agent to use delimiters or boundary markers to distinguish between data and instructions when processing fetched content.\n
  • Capability inventory: The agent has permissions to execute shell commands, perform network operations via a GitHub token, and modify local source files.\n
  • Sanitization: There is no evidence of data sanitization or validation specified in the skill instructions to prevent the execution of instructions found in external GitHub content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:37 PM