aep-git-ref

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill outlines a workflow where the agent ingests data from external sources to drive its actions.\n
  • Ingestion points: The agent is instructed to read tasks.md and files within the openspec/ directory to implement changes and generate commit messages.\n
  • Boundary markers: There are no specific instructions or delimiters provided to isolate untrusted data in these files from the agent's core instructions, creating a risk that malicious input could influence the agent's behavior.\n
  • Capability inventory: The skill grants the agent extensive control over the git repository, including branch management, committing code, and pushing to remote repositories via git and the GitHub CLI (gh).\n
  • Sanitization: No sanitization or validation mechanisms are described for the data read from the task or specification files.\n- [COMMAND_EXECUTION]: The skill includes numerous templates for bash commands that execute git and gh. While these are standard for the skill's purpose, they provide a powerful capability tier that could be exploited if the agent follows malicious instructions from an external file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 11:01 AM
Security Audit — agent-trust-hub — aep-git-ref