Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
PsyClaw PHQ-9
v0.1.0Conduct structured PHQ-9 depression symptom screening and submit the completed assessment for evaluation.
⭐ 0· 45·0 current·0 all-time
by@anctro
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 name and description (PHQ‑9 screening + submission) line up with the instructions to fetch an assessment definition, compute scores locally, and POST the JSON back to the platform. The precondition referencing the companion skill (psyclaw-openclaw-health) is plausible for platform integration, but it's only a recommendation rather than an enforced dependency.
Instruction Scope
SKILL.md / phq9.md instruct the agent to call the platform assessment API to fetch a definition and then POST results to $AGENT_PLATFORM_BASE_URL/api/v1/assessments/submit using an Authorization Bearer token. The instructions reference a local credentials path (.agents/skill-docs/openclaw-health/credentials.json) and require network calls and an API key, yet the skill does not declare these needs. While the described actions are within the PHQ‑9 use case, the runtime instructions reference config/env items that are not documented in the skill metadata (scope/inventory mismatch).
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest install risk. It does recommend (in SKILL.md) running an npx command to install a companion skill (psyclaw-openclaw-health), which would pull code from npm if executed; that recommendation is not the same as an automated install but users should review that package before running npx.
Credentials
The runtime instructions clearly require an agent platform base URL and an agent API key (used as Bearer token) and reference a local credentials.json path, but the skill's metadata declares no required env vars, no primary credential, and no required config paths. This omission is a proportionality/consistency problem: the necessary secrets and config locations are not declared in the skill manifest.
Persistence & Privilege
The skill does not request persistent presence (always: false), does not include install-time code, and does not ask to modify broader agent settings. Autonomous invocation is allowed (platform default) but not, by itself, a red flag here.
What to consider before installing
This skill appears to do what it claims (collect PHQ‑9 answers, compute scores, and POST a JSON to your assessment platform), but the SKILL.md references an API base URL, a Bearer API key, and a local credentials.json path that are not declared in the skill metadata. Before installing or running it, verify: 1) where results are posted (confirm $AGENT_PLATFORM_BASE_URL is your trusted platform); 2) you have, and are willing to provide, the required API key/token (do not paste secret keys into untrusted prompts); 3) the referenced credentials file path (.agents/skill-docs/openclaw-health/credentials.json) and any companion package (psyclaw-openclaw-health) are legitimate — inspect that package before running npx to install it; and 4) that submitting sensitive assessment data to the configured endpoint complies with your privacy/legal requirements. The main issue is an omitted declaration of required environment variables and config paths — ask the skill author to explicitly list required env vars (AGENT_PLATFORM_BASE_URL, AGENT API KEY or name) and confirm the endpoint and credential storage location before use.Like a lobster shell, security has layers — review code before you run it.
assessmentvk97c7qe73w3rafmxqnhh98381h83qa3alatestvk97c7qe73w3rafmxqnhh98381h83qa3aphq9vk97c7qe73w3rafmxqnhh98381h83qa3a
License
MIT-0
Free to use, modify, and redistribute. No attribution required.