troubleshooting-guide
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically system logs and execution traces, which can serve as a vector for indirect prompt injection attacks.
- Ingestion points: Defined in SKILL.md under Step 1, which instructs the agent to "Pull recent logs, traces".
- Boundary markers: The instructions do not define specific delimiters or boundary markers (e.g., XML tags or clear separators) to encapsulate external log data, making it harder for the model to distinguish between log content and system instructions.
- Capability inventory: The skill generates a TASKS_TEMPLATE.md which includes instructions for the agent to perform file system operations and execute command-line interface tools such as prisma, tsc, and eslint.
- Sanitization: Although Section 2 of the Security & Guardrails in SKILL.md explicitly mentions the risk of "Log Forgery Context Poisoning" and the need for sanitization, the skill does not implement or enforce any specific sanitization logic for the ingested data.
Audit Metadata