client-onboarding
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external local files which could potentially contain malicious instructions.
- Ingestion points: Reads brand profiles (
profile.json), guidelines (_manifest.json), and agency SOPs from the~/.claude-marketing/directory inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing these files.
- Capability inventory: The skill uses the
marketing-strategistagent to orchestrate workflows and generate structured text documents (kickoff agendas, questionnaires, milestone plans). - Sanitization: There is no mention of sanitizing or validating the content retrieved from the local JSON and markdown files before interpolation into the output.
Audit Metadata