pasm-cs-agent@0.6.0
CAUTION· static onlyPublisher claims: "Customer-service agents built on the PASM cognitive engine. CustomerServiceAgent answers only from knowledge facts (entries carrying a source) and applies a relevance gate that requires the match to land on the entry's title or tags - so it refuses to answer instead of answering the wrong thing (measured: true hits score 6.0-24.5 while a bogus hit via one incidental word scored 2.29). Complaint phrases in four classes are detected and escalated into salience-5 memory that small talk can never evict, returning escalation context for your notifier. Knowledge is ingested incrementally with content-fingerprint de-duplication, and each agent gets its own KB directory so multiple tenants on one host cannot leak into each other. Optional vendor-neutral LLM with automatic fallback to KB answering. Keywords: pasm, customer service, knowledge base, FAQ, escalation, offline." 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 2026-11-18 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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
No findings across 426 lines in 2 files.
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
9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim arronjack: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.