Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only prompt-compression skill with clear warnings that its action-like notation should be reviewed before use in execution tools.
Before installing, understand that this skill produces compact command-like text. It does not execute actions itself, but you should review any output containing destructive or broad terms such as DEL, WRIT, SYNC, @LOCAL, @DRIVE, or @R2 before giving it to another agent or automation system that might act on it.
This manifest-like JSON uses a natural-language input phrase as the apparent trigger, but "Translate this document to Chinese and save it to cloud storage" is broad enough to overlap with ordinary user requests. The file provides no explicit trigger scope, exclusions, or negative examples to clarify when this skill should or should not activate.
The natural-language input and transformation output both hard-code translation to Chinese ("lng=zh") with no indication that the user can choose another language or opt in to this locale constraint. This can violate language/locale policy expectations when a skill imposes a specific language without documented justification.
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
Data I/O: READ, WRIT, DEL, LIST, COPY, MOVE, STRM, CACH, SYNC, Π
Transform: Σ, Δ, φ, ∇, DEDU, ∂, CHNK, FLAT, NEST, λ, REDU, PIVT, TRNS, ENCD, DECD, ξ, ζ, EXPN, θ, FMT
Analysis: ψ, CLST, SCOR, BNCH, AUDT, VALD, CNT, μ, TRND, CORR, FRCS, ANOM
Generation: CREA, DRFT, PARA, EXPD, SHRT, STYL, TMPL, FILL
Output: Ω, DISP, EXPT, PRNT, LOG
Meta: HELP, DESC, INTR, NOOP
Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
Data I/O: READ, WRIT, DEL, LIST, COPY, MOVE, STRM, CACH, SYNC, Π
Transform: Σ, Δ, φ, ∇, DEDU, ∂, CHNK, FLAT, NEST, λ, REDU, PIVT, TRNS, ENCD, DECD, ξ, ζ, EXPN, θ, FMT
Analysis: ψ, CLST, SCOR, BNCH, AUDT, VALD, CNT, μ, TRND, CORR, FRCS, ANOM
Generation: CREA, DRFT, PARA, EXPD, SHRT, STYL, TMPL, FILL
Output: Ω, DISP, EXPT, PRNT, LOG
Meta: HELP, DESC, INTR, NOOP
This manifest describes the skill generically as compressing natural language prompts into I-Lang, but it does not provide any explicit trigger phrases, scope constraints, or exclusion conditions. For a manifest file, that ambiguity can make it unclear when the skill should be invoked versus ordinary prompt-editing or summarization tasks.
No suspicious patterns detected.