finishing-a-development-branch

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface detected where untrusted external data enters the agent context.
  • Ingestion points: Branch names, commit lists, and output from various test runners (npm, cargo, pytest, go) as described in SKILL.md.
  • Boundary markers: Absent; delimiters are not used when processing these data points.
  • Capability inventory: Execution of shell commands including git, gh, and multiple language test runners in SKILL.md.
  • Sanitization: No sanitization or escaping of the external content is implemented.
  • [COMMAND_EXECUTION]: The skill executes standard version control and development tool commands as part of its core functionality.
  • Evidence: Uses git for branch operations, gh for repository management on GitHub, and various ecosystem-standard test commands. These operations are aligned with the skill's stated purpose of finishing development branches.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 06:10 PM
Security Audit — agent-trust-hub — finishing-a-development-branch