retargeting-strategy
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script named
campaign-tracker.pyusing a 'slug' identifier as a command-line argument. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from local configuration files into the agent's context.
- Ingestion points: Data is read from
~/.claude-marketing/brands/_active-brand.jsonand~/.claude-marketing/brands/{slug}/profile.json. - Boundary markers: No delimiters or specific instructions are provided to prevent the agent from obeying instructions embedded within these files.
- Capability inventory: The skill has the ability to execute subprocesses and read from the local filesystem.
- Sanitization: There is no evidence of validation or sanitization for the data read from the JSON configuration files before it is used in logic or commands.
Audit Metadata