find-conferences
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill configuration uses restricted bash commands and scopes file operations to specific local paths. No malicious patterns, obfuscation, or data exfiltration attempts were identified.- [SAFE]: Analysis of the indirect prompt injection surface shows that while the skill ingests untrusted web data via WebSearch and WebFetch, it lacks the dangerous capabilities required for a successful exploit.
- Ingestion points: External web content retrieved via WebSearch and WebFetch (Step 2).
- Boundary markers: None explicitly defined to separate untrusted web content from system instructions.
- Capability inventory: Restricted Bash tools (mkdir, test, date), Read (ground-truth.md), and Write (conferences.md).
- Sanitization: No programmatic sanitization is specified for retrieved web content.
- Risk Assessment: The risk is negligible as the agent's capabilities are limited to formatting information into Markdown files and performing basic directory management.
Audit Metadata