to-tickets
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as specifications, design documents, or URLs to generate project tickets. This creates an attack surface where a malicious document could influence the agent's behavior.
- Ingestion points: Step 1 in
SKILL.mdinstructs the agent to fetch and read external references provided by the user in full. - Boundary markers: The instructions lack explicit boundary markers or warnings to ignore instructions embedded within the fetched external data.
- Capability inventory: Step 6 in
SKILL.mdpermits the agent to write the resulting content directly into the project's issue tracker. - Sanitization: No sanitization, escaping, or validation of the external content is performed before interpolation into the ticket generation process.
Audit Metadata