ds-content-perf

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: Data from Google Analytics 4 (GA4) and Search Console (GSC), specifically page titles and URLs, are processed in Step 2.
  • Boundary markers: The skill does not implement explicit boundary markers or delimiters when interpolating ingested analytics data into the prompt for the final report generation phase.
  • Capability inventory: The skill has access to a restricted Bash tool (limited to ds_utils.py), MCP analytics tools, and local file reading capabilities.
  • Sanitization: While the skill uses ds_utils.py to clean UTM parameters and aggregate URLs, it does not perform sanitization to detect or neutralize natural language instructions embedded within the processed data.
  • [COMMAND_EXECUTION]: The skill uses local command execution for data processing and context loading.
  • Evidence: The frontmatter limits the Bash tool to executing a specific Python utility script (ds_utils.py).
  • Evidence: The skill uses a cat command to read business context from a local path (.agents/product-marketing-context.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 03:40 AM