persian-brand-copy
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and configuration files aimed at improving the quality and accuracy of Persian-language marketing copy. It does not contain executable code, shell commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied briefs and brand examples, which constitutes a potential injection surface. However, the skill explicitly provides a detailed 'Evidence and public-data policy' (references/evidence-policy.md) that instructs the agent to separate user-supplied facts from creative choices, classify claims, and mark unverified content. These instructions serve as internal boundary markers to mitigate the risk of untrusted data influencing the agent's core instructions.
- [EXTERNAL_DOWNLOADS]: The skill references several external resources for orthography and writing standards, including the official Iranian Academy of Persian Language and Literature (apll.ir) and Unicode CLDR. These are legitimate, well-known references for the skill's stated purpose and do not represent a security risk.
- [NO_CODE]: The skill does not include any scripts or automation logic; it functions purely as a set of sophisticated prompt instructions for the AI agent.
Audit Metadata