cs-onboard
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface by ingesting untrusted input from a user interview and persisting it into a local file (~/.claude/company-context.md) intended for use by other agent skills.
- Ingestion points: User input provided during the /cs:setup and /cs:update interview commands defined in SKILL.md.
- Boundary markers: The templates/company-context-template.md uses standard Markdown headers but lacks explicit instructions or delimiters to prevent the agent from following instructions embedded within the interview answers.
- Capability inventory: The skill has the capability to write to the local filesystem to create and update the context file.
- Sanitization: There is no evidence of input validation, escaping, or filtering for the data captured during the interview.
- [SAFE]: The skill performs its stated purpose of capturing company context for advisory roles. The filesystem operations are restricted to the local ~/.claude/ directory, and no network operations, remote code execution, or credential exposure patterns were found.
Audit Metadata