claude-config-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data by reading local configuration files to provide analysis and recommendations.
- Ingestion points: The agent is instructed in
SKILL.mdto readCLAUDE.md,.claude/skills/*.md,.claude/agents/*.md,.claude/commands/*.md, and.claude/hooks/scripts to perform its review. - Boundary markers: There are no specific boundary markers, delimiters, or 'ignore embedded instructions' prompts defined for the ingested file content to prevent the agent from accidentally following instructions found within those files.
- Capability inventory: The skill's defined functionality is limited to providing textual evaluations and design templates; it does not include high-risk capabilities such as file writing, shell command execution, or network exfiltration.
- Sanitization: The instructions do not include any explicit sanitization, filtering, or validation steps for the content of the project files being reviewed.
Audit Metadata