content-decay-scan

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local Python script creative-fatigue-predictor.py during the decay scoring phase (Step 3). This script is used to process performance data and calculate scores, representing a standard command execution pattern within the agent's environment.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting untrusted external data that is subsequently used to influence agent outputs (Category 8).
  • Ingestion points: External data is ingested via sitemaps, URL lists, and exported CSV analytics data as described in the 'Input Required' and 'Process' (Step 2) sections.
  • Boundary markers: There are no explicit boundary markers or instructions provided to the agent to disregard natural language instructions that might be embedded within the ingested URLs or CSV data.
  • Capability inventory: The skill possesses capabilities to execute local scripts (creative-fatigue-predictor.py) and perform detailed content strategy generation via the content-creator and seo-specialist agents.
  • Sanitization: No sanitization, validation, or escaping of the external content is mentioned before it is processed by the agents or the scoring script.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 01:58 PM
Security Audit — agent-trust-hub — content-decay-scan