clawdtm-advisor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Install workflow explicitly fetches and writes community-contributed skill files from the public API (GET https://clawdtm.com/api/v1/skills/install?slug=...), which are untrusted third-party content (often from GitHub/community authors) that the agent is instructed to ingest and install, and those files could contain instructions or code that materially change agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to call the install endpoint (https://clawdtm.com/api/v1/skills/install?slug=SKILL_SLUG) at runtime to fetch a "files" array that can include scripts (e.g., scripts/setup.sh) which are written to disk and executed to activate the skill, so remote content fetched from that URL can directly control prompts/execute code.