lead-research-assistant

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious instructions, obfuscation, or unauthorized code execution patterns were detected within the skill content.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web data, creating an indirect prompt injection surface. Ingestion points: Data retrieved from external websites via the WebSearch tool (SKILL.md, Step 4). Boundary markers: Absent; the instructions do not explicitly tell the agent to ignore instructions embedded in the search results. Capability inventory: The skill is limited to generating text-based analysis, outreach strategies, and CSV formatted data; it does not possess high-risk capabilities like code execution or file-system writing. Sanitization: No sanitization or validation of retrieved web content is performed.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill analyzes the user's codebase to gather product context (SKILL.md, Step 2). This access is a functional requirement for its lead generation purpose and does not target sensitive system files or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:47 PM