Facticity.AI Complete Integration
v0.1.0Complete Facticity.AI integration - fact-check claims, extract claims from content, transcribe links, check link reliability, check credits, and monitor task...
⭐ 0· 426·0 current·0 all-time
by@shahruj
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill name/description map directly to the declared behavior: it calls Facticity.AI endpoints to fact-check, extract claims, transcribe links, check credits, and monitor tasks. The only credential requested is FACTICITY_API_KEY, which is appropriate for an API integration; no unrelated binaries, config paths, or extra credentials are required.
Instruction Scope
SKILL.md limits runtime actions to HTTP calls to https://api.facticity.ai and to verifying the presence of FACTICITY_API_KEY. Two items to be aware of: (1) the docs instruct the agent to "return the JSON response verbatim" — if the API response includes sensitive fields (the README/example shows an `api_key` field), this could cause the key to be echoed into chat/output; (2) the README recommends storing the API key in ~/.openclaw/openclaw.json, which is normal but means the key will reside on disk and should be protected. Aside from these notes, instructions don't scope creep into unrelated system files or other credentials.
Install Mechanism
There is no install spec and no code files — the skill is instruction-only and relies on existing HTTP call tooling. This minimizes risk from arbitrary code being written to disk.
Credentials
Only FACTICITY_API_KEY is required and it is declared as the primary credential. That is proportionate for an HTTP API integration. The skill suggests optionally adding the key to an OpenClaw config file (~/.openclaw/openclaw.json); this is a convenience but has the usual local-storage tradeoffs.
Persistence & Privilege
The skill does not request always: true, does not include installers that change system-wide configuration, and does not modify other skills. It runs on-demand and only uses the declared API key.
Assessment
This skill appears to be a straightforward HTTP integration with Facticity.AI and only needs your FACTICITY_API_KEY. Before installing: (1) confirm the API domain (app.facticity.ai / api.facticity.ai) and documentation are legitimate; (2) be cautious where you store the API key — adding it to ~/.openclaw/openclaw.json is convenient but means the key is on disk; protect that file and your account credentials; (3) test the /get-credits endpoint and avoid commands that would cause the agent to echo any sensitive fields — the SKILL.md asks to return API responses verbatim and example output shows an `api_key` field, which could leak the key if the service returns it unmasked; (4) if you need higher assurance, ask the publisher for a homepage or source repo or request the skill include minimal redaction logic so responses don't reveal secrets. Overall the skill is internally coherent, but follow standard key-handling hygiene.Like a lobster shell, security has layers — review code before you run it.
claimsvk97ejbez2y6s2tp1sw3kp09bz181qqdnfact-checkingvk97ejbez2y6s2tp1sw3kp09bz181qqdnlatestvk97ejbez2y6s2tp1sw3kp09bz181qqdnmultimediavk97ejbez2y6s2tp1sw3kp09bz181qqdnreliabilityvk97ejbez2y6s2tp1sw3kp09bz181qqdnresearch-agentvk97ejbez2y6s2tp1sw3kp09bz181qqdntranscriptionvk97ejbez2y6s2tp1sw3kp09bz181qqdnverificationvk97ejbez2y6s2tp1sw3kp09bz181qqdn
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🔍 Clawdis
EnvFACTICITY_API_KEY
Primary envFACTICITY_API_KEY