gen-smoke
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behaviors, obfuscation, or unauthorized access patterns were detected. The skill's functionality is limited to testing interpreter capabilities through a single file-write operation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes a user-supplied argument (name) and interpolates it into the output written to report.md. This constitutes a theoretical indirect prompt injection surface.
- Ingestion points: The --arg name parameter in SKILL.md frontmatter.
- Boundary markers: None; the variable is placed directly into the string template.
- Capability inventory: Uses the write_artifact tool to write to report.md.
- Sanitization: No sanitization or validation of the name argument is observed.
Audit Metadata