cs-market-research

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and does not contain any executable scripts, shell commands, or remote dependencies.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze data from external sources, including product documentation, source repositories, and search results. This constitutes a surface for indirect prompt injection.
  • Ingestion points: External sources such as product docs, source code, and release notes referenced in Step 2.
  • Boundary markers: The instructions do not define specific delimiters for external content but do advise the agent to verify claims and flag suspicious automation approaches.
  • Capability inventory: The skill allows the agent to read and write project context, mindmaps, features, and tasks.
  • Sanitization: No programmatic sanitization is defined, though the instructions provide a high-level safety guideline to flag credential-scraping or GUI-injection approaches.
  • [DATA_EXPOSURE_&_EXFILTRATION]: No hardcoded credentials or sensitive file paths were identified. While the skill interacts with project metadata (PRDs, tasks, mindmaps), this occurs within the expected environment of the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 07:59 AM
Security Audit — agent-trust-hub — cs-market-research