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