review-hog-blind-spots-general
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of pull request chunks and external review findings. This presents a potential surface for indirect prompt injection if malicious content is present in the reviewed code. 1. Ingestion points: Input includes pull request chunks and findings from other review perspectives as mentioned in the instructions. 2. Boundary markers: None explicitly defined within the instruction text. 3. Capability inventory: The skill does not define any active capabilities such as tool usage, file system access, or network operations. 4. Sanitization: Not specified in the provided instructions.
- [NO_CODE]: The skill consists entirely of instructional markdown and metadata, with no accompanying scripts or executable files.
Audit Metadata