pr-generator
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes data from git commit logs and file diffs. Maliciously crafted commit messages or code changes from other contributors could potentially influence the agent's behavior during the summary generation process.\n
- Ingestion points: Git commit history and diff statistics via
git logandgit diffcommands inSKILL.md.\n - Boundary markers: None. The skill does not wrap the retrieved git data in delimiters or instruct the agent to ignore instructions contained within the data.\n
- Capability inventory: Execution of shell commands for git operations.\n
- Sanitization: None. The skill processes the raw output of git commands.\n- [COMMAND_EXECUTION]: User-provided branch names are directly interpolated into shell commands (e.g.,
git log <target-branch>..HEAD). While typically used in a personal development environment, this pattern allows unvalidated input to influence command execution, which could be exploited if the skill is used in a shared or automated context.
Audit Metadata