commit-conventions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Prompt Injection (LOW): The skill is susceptible to indirect prompt injection because it analyzes external, potentially untrusted data from git diffs.\n
- Ingestion points: The skill ingests data from
git diff --stagedand files within the.context/directory (e.g.,conventions.md,specs/).\n - Boundary markers: The instructions do not define clear delimiters to separate the untrusted diff content from the agent's logic, increasing the risk that embedded instructions in code comments could be followed.\n
- Capability inventory: The skill is limited to text generation and does not have the ability to execute shell commands, write files, or access the network.\n
- Sanitization: There is no evidence of sanitization or filtering of the input diff data before it is processed by the LLM.\n- No Code (SAFE): The skill consists entirely of markdown instructions and templates without any associated scripts, binaries, or package dependencies.
Audit Metadata