reporting-guideline-compliance-checker
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected across the analyzed files. The skill functions solely as a cognitive assistant for academic writing and reporting compliance.
- [NO_CODE]: The skill consists entirely of markdown instructions and reference modules. It does not install packages, execute scripts, or utilize external binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface by ingesting untrusted data such as manuscript drafts and reviewer comments.
- Ingestion points: User-provided manuscripts and drafts defined in the 'Input Validation' section of SKILL.md.
- Boundary markers: Absent; the instructions do not specify delimiters for user text.
- Capability inventory: None; the skill has no access to shell commands, network tools, or file system write operations across all provided scripts and instructions.
- Sanitization: Absent; the skill relies on internal 'Hard Rules' in SKILL.md and references/hard-rules.md to prevent following instructions within the data. Given the total lack of exploitable capabilities, the risk associated with this surface is negligible.
Audit Metadata