marketing-context
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill includes local Python scripts (scripts/competitive_landscape_mapper.py, scripts/context_completeness_checker.py, and scripts/icp_fit_scorer.py) that facilitate marketing analysis. These scripts utilize only standard libraries (json, sys, argparse, re) and perform benign data processing.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to study project documentation, landing pages, and marketing copy to draft context documents. This represents a potential surface for indirect prompt injection if the ingested files contain adversarial instructions. However, the risk is minimal as the skill does not provide the agent with high-privilege capabilities such as network access or shell execution. 1. Ingestion points: README, landing pages, and documentation referenced in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Local data mapping and scoring utility scripts. 4. Sanitization: Absent.
Audit Metadata