dot-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks for app_id/app_secret, OAuth codes and access tokens and shows examples that place those secrets verbatim into command-line flags and Authorization headers (e.g., --user-token {user_access_token}, Header: Authorization: Bearer {app_access_token}), requiring the agent to handle/output secret values directly, which is high-risk.

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

• Third-party content exposure detected (high risk: 0.95). Runtime path: the skill’s Feishu auto-collector (tools/feishu_auto_collector.py) fetches outsider-authored Feishu messages/docs/Wiki content from other users’ accounts via Feishu APIs, then writes readable prose into knowledge/{slug}/messages.txt and docs.txt which are later ingested by the LLM for analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The README/INSTALL.md explicitly instructs cloning and running the remote repository (git clone https://github.com/titanwings/colleague-skill followed by running python tools/install_*.py), which fetches remote code at runtime and then executes it, so https://github.com/titanwings/colleague-skill is a runtime external dependency that can execute remote code.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)