market-research

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill performs network operations to external API providers such as Perplexity to conduct deep research. This involves transmitting user-defined search queries to these services.- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted data from external research providers.
  • Ingestion points: Research responses from external deep research APIs in Step 2.
  • Boundary markers: No explicit markers or instructions to ignore embedded commands are present.
  • Capability inventory: The skill writes research data and distilled hypotheses to the local file system at claude-code-gtm/context/{vertical-slug}/.
  • Sanitization: The skill does not explicitly describe sanitization or validation of the fetched data before distillation and storage.- [COMMAND_EXECUTION]: The skill interacts with the local file system to read company context files and write research outputs to the claude-code-gtm/context/ directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 09:41 PM