AC fact-checker
Fact-check news articles, social media posts, images, and videos. Use when verifying claims, detecting deepfakes or AI-generated content, identifying out-of-context media, or debunking misinformation. Any language.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
AnalyzerInfrastructureMedia and videoWriting and documentstype and topics are labelled automatically from the skill text
How to improve
For the model run — optional
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 2
✓ No critical or high findings
Medium and low: 2
-
low Exfiltration
exfil-secret-in-urlreferences/api_docs.md:19Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (destination is a well-known publishing service; quoted — discussed, not commanded)curl -s "https://factchecktools.googleapis.com/v1alpha1/claims:search?query=…&languageCode=en&pageSize=10&key=…"
known servicequoted -
low Exfiltration
net-credential-usereferences/api_docs.md:19Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)curl -s "https://factchecktools.googleapis.com/v1alpha1/claims:search?query=…&languageCode=en&pageSize=10&key=…"
known service
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (fact-checker) differs from the folder (openclaw-fact-checker)
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 100Steps. 33 steps
- 100Failures and branches. 7 branches, has a failure section
- 100Execution cost. Instruction body is 1859 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 214: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.
External checks
ClawHub: suspicious
This is a coherent fact-checking skill, but it needs Review because it can send user content or extracted audio to third-party APIs, prints API keys while checking them, and can persistently change future agent routing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026