competitor-analysis

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

• Third-party content exposure detected (medium risk: 0.30). In the enrichment “Gate” stage, scripts/gate_candidates.mjs takes an outsider-influenced candidate URL list and runs browse cloud fetch --format raw to read up to the page’s <title> and first 800 visible characters for classification.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs the user/agent to permanently approve and bypass interactive tool permission prompts by editing ~/.claude/settings.json and to batch file-write and command approvals, which is a directive to circumvent security prompts and thus risks compromising the host state.