lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were detected within the skill's instructions or metadata.- [NO_CODE]: The skill consists entirely of markdown instructions and documentation; it does not include any scripts, binaries, or configuration files that execute code.- [PROMPT_INJECTION]: The skill instructions do not contain attempts to override safety filters, disregard previous instructions, or extract system prompts. An evaluation of indirect prompt injection surfaces (Category 8) shows: 1. Ingestion points: The skill analyzes local codebase files and external search results. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: The skill utilizes file reading and web searching capabilities. 4. Sanitization: No sanitization or validation of the ingested content is specified. While this creates a theoretical surface for indirect injection, the instructions themselves are benign and professional in nature.
Audit Metadata