brand-manifesto
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for a brand writer persona to generate manifestos based on user-provided beliefs and convictions.
- [DATA_EXPOSURE]: The skill reads context from
.agents/brand-context.mdand other brand-related documentation. This is a local operation intended to align the generated text with the brand's established strategy and does not involve accessing sensitive system information or credentials. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local brand files (e.g.,
.agents/brand-context.md). However, since the skill has no capabilities for network exfiltration or command execution, the surface for exploiting this injection is negligible. - Ingestion points:
.agents/brand-context.md, brand strategy, story, or positioning files. - Boundary markers: Not specified.
- Capability inventory: None (no subprocess, network, or file-write operations detected).
- Sanitization: Not specified.
Audit Metadata