writing
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as obfuscation, credential exfiltration, or unauthorized command execution were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the conversation's shared history. While the skill lacks high-risk capabilities like network access or file writing, it does not employ explicit boundary markers or sanitization for this external content. 1. Ingestion points: Shared history (SKILL.md) 2. Boundary markers: Absent 3. Capability inventory: count_characters tool (SKILL.md) 4. Sanitization: Absent.
Audit Metadata