locate-review-research-gap
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied literature reviews to identify research gaps. This creates a theoretical ingestion surface for indirect prompt injection if the processed data contains instructions meant to hijack the agent's behavior. However, because the skill has no destructive capabilities (no shell access, no file system writes, and no network operations), the resulting risk is negligible.
- Ingestion points: Untrusted text from user literature reviews (SKILL.md).
- Boundary markers: Absent; there are no explicit delimiters or warnings to ignore instructions within the user data.
- Capability inventory: Zero. The skill does not invoke any tools, subprocesses, or network calls.
- Sanitization: No sanitization or filtering is applied to the ingested text.
- [NO_CODE]: The skill consists entirely of instructional markdown and a static interface configuration. It does not include or reference any scripts, executables, or third-party dependencies.
Audit Metadata