Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Lead Discovery
v1.2.0AI-driven lead discovery for B2B export. Searches web for potential buyers matching ICP, evaluates fit, and creates CRM records for follow-up.
⭐ 0· 74·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill's stated purpose (web lead discovery) matches the instructions (search, read websites, score leads). However the runtime instructions require a JINA_API_KEY and CRM interaction (implicit), which are plausible needs but are not declared in the skill metadata; that mismatch is incoherent and unexplained.
Instruction Scope
SKILL.md explicitly instructs the agent to read company websites via Jina Reader and perform searches, but also references reading .secrets/env, USER.md, storing notes in 'Supermemory', checking/writing CRM records and scheduling cron jobs. USER.md, CRM endpoints/credentials, and the Supermemory config are not included or referenced in metadata — the instructions ask for access to files/configs that are not declared and could expose unrelated secrets or data.
Install Mechanism
This is an instruction-only skill with no install spec or code files, so there is no installer risk (nothing is downloaded or written by an installer).
Credentials
The runtime examples require a JINA_API_KEY (used in curl Authorization header) and mention a .secrets/env file, yet requires.env is empty in the registry. The skill will also need CRM credentials to write leads but does not declare them. Requesting or reading undeclared secret locations is disproportionate and could lead to accidental exposure of unrelated credentials.
Persistence & Privilege
always:false (good) and autonomous invocation is allowed (default). The instructions describe cron-triggered runs and storing notes in 'Supermemory' — this implies ongoing writes to the agent's memory/CRM but the skill does not request elevated platform privileges. Still, persistent scheduled behavior and automatic writes amplify risk if credential/config details are wrong or broad.
What to consider before installing
Do not install or enable this skill until the author clarifies and fixes the metadata/instructions. Key questions to ask or steps to take: 1) Provide a complete list of required environment variables and config paths (e.g., JINA_API_KEY, CRM_API_KEY, path to Supermemory) in requires.env and required config paths. 2) Explain where USER.md and Supermemory live and provide their schemas; ensure the skill will not read arbitrary files like .secrets/env unless explicitly authorized. 3) Provide the exact CRM integration details (endpoint, auth method, scopes) and demonstrate least-privilege credentials. 4) Run the skill in a sandbox/staging agent with test credentials and monitor network calls and file reads before enabling on production data. 5) If you must proceed, restrict it to manual invocation until credentials and data-handling behaviour are audited, and rotate any test credentials used for verification afterwards.Like a lobster shell, security has layers — review code before you run it.
latestvk9750rpy7smp9xa1fbam6zzmxh83jcst
License
MIT-0
Free to use, modify, and redistribute. No attribution required.