brief
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill automatically loads content from
~/.claude/company-context.mdas specified in the Inputs section ofSKILL.md. Although this file is required for the primary function of strategy framing, accessing files in hidden directories represents a potential data exposure surface. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data which could contain malicious instructions. 1. Ingestion points: User-supplied
<topic>or<office-hours-output>and the contents of~/.claude/company-context.md(SKILL.md). 2. Boundary markers: Absent; there are no instructions to the agent to treat input as data rather than instructions. 3. Capability inventory: The skill writes generated content to the local file system at~/.claude/briefs/(SKILL.md). 4. Sanitization: Absent; there is no mention of input filtering or escaping.
Audit Metadata