social-post-writer-seo
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were detected within the skill instructions.
- [NO_CODE]: The skill is entirely composed of natural language instructions and prompt templates; it contains no scripts, shell commands, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill uses variables to interpolate user-provided data into its generation logic.
- Ingestion points: User-supplied input variables such as {Insert Topic}, {Insert Keyword}, {Target Audience}, and {Brand} in
SKILL.md. - Boundary markers: None; user inputs are directly inserted into the instructional template.
- Capability inventory: No capabilities for file system access, network communication, or subprocess execution are present.
- Sanitization: None detected. However, the lack of hazardous capabilities renders this injection surface benign.
Audit Metadata