Persian
v1.0.0Write Persian that sounds human. Not formal, not robotic, not AI-generated.
⭐ 2· 688·0 current·0 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name and description (produce natural, non‑formal Persian) align with the SKILL.md content. The instructions are stylistic guidance and require no binaries, credentials, or unrelated capabilities.
Instruction Scope
The instructions are narrowly scoped to tone, colloquial patterns, particles, and a simple 'Native Test' heuristic. However, the pre-scan detected unicode control characters embedded in the SKILL.md, which can be used for stealthy prompt-injection or to alter how parsers/validators read the file—inspect the raw file for zero-width/formatting codepoints before deploying.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk install model; nothing is written to disk by an installer.
Credentials
The skill declares no environment variables, credentials, or config paths. There is no disproportionate request for secrets or external access relative to the stated purpose.
Persistence & Privilege
Defaults (always: false, agent-invocable, model invocation enabled) are reasonable for a language-style helper. The skill does not request elevated or persistent privileges.
Scan Findings in Context
[unicode-control-chars] unexpected: Hidden Unicode control or zero-width characters were detected inside SKILL.md. These are not needed for style guidance and may be used to hide instructions or change how other tools parse the file. Recommend examining the raw bytes or viewing with an editor/show‑invisibles to remove unexpected control characters (e.g., U+200B ZERO WIDTH SPACE, U+200E LRM, U+202A).
Assessment
This skill is internally coherent: it only provides stylistic rules for writing casual Persian and asks for nothing else. Before installing, open the SKILL.md in a text editor that shows invisible characters (or run a small script to list non-printable Unicode codepoints) and remove any unexpected zero-width or directional control characters. After installing, test the skill with a few representative prompts to confirm outputs match the casual tone you want. Because the skill can be invoked by agents, monitor initial runs for any unexpected behavior, though no other red flags were found.Like a lobster shell, security has layers — review code before you run it.
latestvk971e17xewte02my77nkfdve3180waah
License
MIT-0
Free to use, modify, and redistribute. No attribution required.