li-prd-review
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill exhibits no signs of malicious intent, obfuscation, or unauthorized data exfiltration. All operations are aligned with the stated purpose of PRD review and optimization.
- [PROMPT_INJECTION]: The skill processes untrusted user-provided PRD content, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill ingest PRD content via text input or specific file paths provided by the user (defined in SKILL.md).
- Boundary markers: Absent; there are no specific instructions or delimiters used to separate the PRD content from the agent's internal logic.
- Capability inventory: The skill has the capability to read and update files to incorporate accepted changes (described in SKILL.md and references/advisors.md).
- Sanitization: No explicit sanitization or filtering of the PRD content is performed before processing.
- [NO_CODE]: The skill consists entirely of Markdown instructions and reference files, with no executable scripts or external code dependencies included.
Audit Metadata