brand-voice
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it instructs the agent to ingest content from an external source (
.agents/brand-context.md). If this file is controlled by an attacker, they could influence the agent's behavior. - Ingestion points: The agent is instructed to read
.agents/brand-context.mdin the 'Before You Start' section of SKILL.md. - Boundary markers: Absent. The instructions do not provide delimiters or warnings to the agent to treat the file content as untrusted data.
- Capability inventory: None. No executable scripts, network tools, or file-writing capabilities were detected in the skill, which significantly limits the potential for harm from an injection attack.
- Sanitization: Absent. The skill does not include any instructions for validating or escaping the content read from the context file.
Audit Metadata