dev-workflows

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from the project environment, creating a surface for indirect prompt injection.\n
  • Ingestion points: The skill is designed to parse build logs, test failure diagnostics, and CI/CD configuration files (e.g., .gitlab-ci.yml, .github/workflows/*.yml) found in the repository.\n
  • Boundary markers: The instructions lack specific guidance on using delimiters or ignoring instructions embedded within these external data sources.\n
  • Capability inventory: The agent has the ability to execute shell commands via Bash, modify project files using Write, and delegate complex diagnostic tasks to subagents.\n
  • Sanitization: There is no evidence of sanitization or validation of the text extracted from logs or configurations before it is used to inform automated 'fixes' or command execution.\n- [COMMAND_EXECUTION]: The skill's primary function involves executing shell commands through Bash to run builds and tests. While this is the intended behavior for a DevOps tool, it provides a powerful capability that could be misused if the agent is influenced by malicious instructions in the project files it analyzes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:41 PM
Security Audit — agent-trust-hub — dev-workflows