code-doubter
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill is comprised entirely of markdown-based instructions within
SKILL.md. There are no associated scripts, executables, or configuration files that could facilitate malicious behavior. - [SAFE]: No patterns associated with data exfiltration, credential harvesting, or unauthorized command execution were detected. The skill does not request or use any external tools or network access.
- [INDIRECT_PROMPT_INJECTION]: Analysis of the attack surface for malicious instructions within user-provided plans:
- Ingestion points: Implementation plans and architecture decisions provided by users in
SKILL.mdfrontmatter. - Boundary markers: None specified; the skill does not instruct the agent to use delimiters when processing user plans.
- Capability inventory: The skill definition contains no subprocess calls, file system write operations, or network requests.
- Sanitization: No input sanitization or escaping instructions are present. Although the skill processes untrusted input, the total lack of exploitable capabilities prevents this from being a viable attack vector.
Audit Metadata