status
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local Python script located at
scripts/dm-status.pyusing thepythoninterpreter to generate its reports. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes external marketing data files.
- Ingestion points: Data is read from brand profile JSON files and engagement logs within the
~/.claude-marketing/brands/directory. - Capability inventory: The skill uses
Bashand executes Python scripts (scripts/dm-status.py) that read file contents, which are then passed to the agent's context. - Boundary markers: The skill does not define any delimiters or boundary markers to differentiate between the retrieved data and the agent's system instructions.
- Sanitization: There is no evidence of data sanitization or filtering to prevent the agent from executing instructions that may be embedded in the marketing profiles or insights.
Audit Metadata