research
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external primary sources such as documentation and first-party APIs, which presents a surface for indirect prompt injection where malicious instructions could be embedded in the source material.
- Ingestion points: Investigates primary sources including official docs, source code, and first-party APIs as described in
SKILL.md. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded instructions mentioned in the skill definition.
- Capability inventory: Capabilities are limited to file system writes of Markdown notes to the
docs/research/directory as noted inSKILL.md. - Sanitization: Absent; the instructions do not provide for sanitization or verification of the content before it is captured in findings.
Audit Metadata