tweet-series-extractor

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements a standard web scraping workflow using authorized browser automation tools to collect public data from a well-known service (X.com). The operations, including navigation and link extraction via JavaScript, are consistent with the skill's stated purpose.- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from X.com into the agent's context.
  • Ingestion points: Page text and DOM data are retrieved from X.com using the get_page_text and read_page tools as described in SKILL.md.
  • Boundary markers: The workflow lacks explicit delimiters or instructions to the agent to treat the retrieved tweet content as untrusted data or to ignore embedded instructions.
  • Capability inventory: The agent has access to browser navigation, DOM reading, and JavaScript execution via the mcp__claude-in-chrome__ toolset.
  • Sanitization: There is no evidence of content sanitization or validation of the retrieved tweet data before it is processed or presented in the output JSON structure.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 05:20 AM