agent-media@1.0.1
CAUTION· static onlyPublisher claims: "AI UGC video production from the terminal using the `agent-media` CLI." Observed in sandbox: static analysis only — behavior not yet observed.
Coverage
Static only; nothing was run yet.The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-21 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Rule modification attempt; Rule modification attempt; Fake instruction boundary tag. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.
Static findings
### Rule 3: SaaS reviews MUST have screenshotsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 5: Always use `--sync`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| `-g, --generate-script <prompt>` | AI-generate script from description | `-g "yoga mat product"` |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 4: SaaS reviews MUST have the product nameFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.**You MUST follow ALL of these rules. Violating any rule produces a broken, unwatchable video.**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 1: ALWAYS use `--actor`Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Rule 2: ALWAYS count words — 2.5 words per secondFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim nevo-david: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.