skills/hainrixz/claude-ads/ads-dna/Gen Agent Trust Hub

ads-dna

Warn

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: In Step 2b, the skill instructs the agent to run python ~/.claude/skills/ads/scripts/capture_screenshot.py [url] using a URL provided by the user. This pattern is vulnerable to command or argument injection if the input is not strictly validated or escaped before execution.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it fetches and processes untrusted content from external URLs to extract brand elements.
  • Ingestion points: HTML and text content retrieved from external websites via the WebFetch tool (Step 2).
  • Boundary markers: Absent. No delimiters or 'ignore embedded instructions' warnings are provided to the agent when processing the fetched content.
  • Capability inventory: Shell execution of local Python scripts and file writing access for JSON and images.
  • Sanitization: Absent. The skill performs no validation or filtering of the fetched web content before analysis.
Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 03:44 PM
Security Audit — agent-trust-hub — ads-dna