write-pr-description
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git commands such as git diff and git log to gather metadata and code changes from the repository.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes the output of git diff, which can include attacker-controlled code containing malicious instructions.
- Ingestion points: Output from git diff and git log is read into the agent context in SKILL.md.
- Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the diff data.
- Capability inventory: The skill utilizes git shell commands for context gathering.
- Sanitization: Absent; the skill does not perform any validation or escaping of the diff content before processing.
Audit Metadata