impl
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and follow instructions from external, potentially untrusted data sources such as project specifications, tickets, and design documents.
- Ingestion points: The skill instructions in
SKILL.md(Step 1) mandate reading specifications, tickets, anddesign.mdto guide implementation. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between data and potentially malicious instructions embedded within these documents.
- Capability inventory: The skill possesses the ability to execute shell commands for typechecking and testing, and to perform git commits (
SKILL.md, Steps 3-5). - Sanitization: No sanitization or validation of the content of these input files is performed before the agent acts upon them.
Audit Metadata