content-decay-scan
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill accesses local configuration files located in
~/.claude-marketing/brands/, including brand profiles, strategy guidelines, and SOPs. This is expected behavior for a marketing analysis tool to ensure responses align with brand identity. - [COMMAND_EXECUTION]: The skill executes a local Python script
creative-fatigue-predictor.pyto perform decay scoring. The script is invoked with specific parameters and data provided in a JSON format. This is a standard mechanism for offloading complex processing to specialized scripts. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data including sitemaps, URLs, and exported analytics CSVs. While this presents a surface for indirect prompt injection, the skill is designed to process this data through a structured Python script, which acts as a layer of separation between the external content and the agent's core instructions.
Audit Metadata