find-signal-leads
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external datasets, creating a surface for indirect prompt injection. 1. Ingestion points:
candidates.jsonl(referenced inSKILL.md). 2. Boundary markers: Absent. 3. Capability inventory:scripts/match_entities.pyreads local files and performs string matching; no network or shell execution capabilities. 4. Sanitization: Thenorm()function in the script performs uppercase conversion and punctuation stripping, reducing the risk of hidden characters or formatting manipulation. - [SAFE]: The skill operates entirely on local files and uses a Python script with standard libraries for processing. No signs of obfuscation, hardcoded credentials, or remote code execution were identified.
Audit Metadata