greptile-address
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it ingests untrusted data from external GitHub comments and uses that data to influence its actions.
- Ingestion points: Untrusted data enters the agent context via
gh apicalls fetching pull request reviews and comments as specified inSKILL.md(Step 3). - Boundary markers: There are no boundary markers or instructions defined to delimit the external comment content or to instruct the agent to ignore embedded commands within those comments.
- Capability inventory: The skill possesses capabilities to modify local files (Step 5) and perform network operations via
git push(Step 7) as described inSKILL.md. - Sanitization: The instructions do not specify any sanitization, filtering, or validation of the fetched comment content before it is processed by the agent.
Audit Metadata