security-review
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
- Ingestion points: Untrusted data enters the agent's context through placeholders for
<git status output>,<list of modified files>,<commit log>, and<full diff>inSKILL.md. - Boundary markers: The skill uses markdown code blocks to delimit untrusted content, which provides some structural separation but does not prevent the LLM from following instructions embedded within those blocks.
- Capability inventory: The skill has access to significant system capabilities via
allowed-tools, includingBash,PowerShell,Read,Glob,Grep,LS, andTask. - Sanitization: There is no evidence of sanitization, escaping, or filtering applied to the ingested git data before it is processed by the agent.
Audit Metadata