client-communication-standards
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's README.md includes a command to download the skill definition from a GitHub repository. This is a standard installation procedure for these skills and utilizes a well-known service belonging to the author.
- [INDIRECT_PROMPT_INJECTION]: The skill handles data findings for report generation, which theoretically exposes the agent to instructions embedded in processed data.
- Ingestion points: External analytics and search reports (e.g., Google Ads, GA4) referenced in the Analysis section of SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the report templates.
- Capability inventory: The skill is restricted to the Read tool in its YAML frontmatter, significantly limiting the potential impact of any injected instructions.
- Sanitization: No sanitization of ingested data is performed before interpolation into the report structure.
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access behaviors were identified. The skill serves a purely instructional and organizational purpose.
Audit Metadata