shaping-work
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on text processing and project planning. It performs standard, local file operations such as reading context files (e.g.,
CLAUDE.md) and saving structured output to the local file system (thoughts/research/). No network activity, credential handling, or dangerous command executions were detected. - [PROMPT_INJECTION]: While the skill processes untrusted user data (Slack threads, customer feedback) which is a surface for indirect prompt injection, the risk is assessed as safe because the output is restricted to generating text documentation and does not trigger executable actions.
- Ingestion points: User-provided 'rough input', Slack threads, and customer complaints (SKILL.md).
- Boundary markers: None explicitly defined for separating instructions from untrusted input.
- Capability inventory: Limited to reading project context and writing markdown files to a specific directory (SKILL.md).
- Sanitization: No explicit sanitization or filtering of input content is specified.
Audit Metadata