launch-plan
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 several local file paths to inform its planning process, creating a surface for instructions embedded in data to influence agent behavior.
- Ingestion points: The skill reads configuration and content from
~/.claude-marketing/brands/_active-brand.json,profile.json,guidelines/_manifest.json, and agency SOPs from~/.claude-marketing/sops/(documented in SKILL.md). - Boundary markers: No delimiters or explicit instructions to ignore embedded commands are specified for the imported file content.
- Capability inventory: Analysis of the skill instructions reveals no capabilities for subprocess calls, code execution (
eval/exec), file writing, or network operations. - Sanitization: No sanitization, escaping, or schema validation of the external content is performed before it is used to generate the playbook.
Audit Metadata