Security audit
Security checks for vulnerabilities and agentic risk
The skill is a disclosed reference-and-simulation package with local read-only verification/simulation scripts, but users should treat the robotics material as conceptual and not hardware-ready.
Install only if you want a broad conceptual Quantum Krump reference/simulation skill. Treat the humanoid robotics values as research or simulation context, not instructions for real hardware deployment, and be aware that some advertised interactive or CLI capabilities appear to live outside this package.
The skill presents itself as a choreography/simulation/teaching tool, yet the flagged behavior indicates integrity auditing and documentation enforcement rather than the declared end-user functions. In agent ecosystems, this can mislead orchestration logic, causing the wrong skill to be selected and potentially exposing filesystem metadata or producing misleading assurance outputs instead of the requested task.
The skill presents itself as a choreography/simulation/teaching tool, yet the flagged behavior indicates integrity auditing and documentation enforcement rather than the declared end-user functions. In agent ecosystems, this can mislead orchestration logic, causing the wrong skill to be selected and potentially exposing filesystem metadata or producing misleading assurance outputs instead of the requested task.
The skill advertises executable commands and references local scripts and documents, but it does not declare an explicit tool scope or permissions boundary. In an agent setting, missing scope declarations can let the runtime infer broader file-read behavior than users expect, increasing the chance of unintended access to local files during verification or reference lookups.
The metadata description says this is a 'multi-domain interconnected knowledge graph' unifying trapped-ion benchmarking, QUBO scheduling, biophysical grounding, symbolic quantum execution, humanoid robotics, and theatrical production. In the file, these appear only as declarative graph entries rather than implemented operations, so the described practical capability exceeds the artifact's actual behavior.
The manifest context describes a usable skill that can choreograph, simulate, analyze, verify, compile movements to circuits, and optimize stage paths. But this file is only a static JSON knowledge graph of domains, nodes, and edges, with no executable logic or tool operations that would perform those actions.
The note states that agents must 'strictly adhere' to calling the gathering a 'session' and 'NEVER' use 'cypher'. This is a natural-language policy constraint that forces a specific terminology choice rather than offering contextual flexibility or user preference.
The document gives concrete high-impact humanoid-robot motion parameters, including a 3.82× body-weight stomp impact and short contact duration, while omitting any explicit safety warnings, operating constraints, or qualification requirements. In the context of a skill that helps users choreograph and simulate physical AI humanoid motion, this could encourage unsafe real-world replication that risks actuator damage, structural overload, falls, or bystander injury.
The persona mandate says to "Strictly use session" and "NEVER use cypher," which is a natural-language output constraint applied to all agent executions. This forces a specific lexical choice regardless of user preference or context, and the file does not offer any user opt-in or exception mechanism.
The line states "Exclusively use session (never cypher)," which is a blanket language policy embedded in the skill description. Because it does not provide user choice or justify the restriction as a documented compliance requirement, it falls under the language-policy concern.
The skill purpose is framed around choreographing, simulating, analyzing, compiling, and teaching quantum-embodied dance. This graph additionally incorporates domestic-violence theatrical narrative and randomized human-subject assessment study concepts, which are not necessary capabilities for the stated tooling purpose and broaden the skill's semantic scope into sensitive narrative and research domains.
This code checks for a hard requirement that SKILL.md must prohibit use of the term 'cypher' and prefer 'session'. That is a natural-language policy constraint embedded in code, but the file provides no indication that users can opt in to this terminology preference or that the constraint is justified by a documented locale or organizational policy.
No suspicious patterns detected.
