pr-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and persona definitions. It does not contain executable scripts, shell commands, or network-enabled tools.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted user data, which is inherent to its primary purpose.
- Ingestion points: The skill ingests user-provided information such as product URLs, product pages, and business descriptions (SKILL.md, Step 1).
- Boundary markers: Explicit delimiters or 'ignore' instructions for user-provided content are absent.
- Capability inventory: The skill's capabilities are limited to text generation and strategy advice; no file-system writes, network requests, or subprocess executions are defined within the skill itself.
- Sanitization: No specific sanitization or filtering of external content is specified.
- Note: Given the skill's purpose as a conversational advisor, this surface is expected and does not present a high risk in the absence of tool-based capabilities.
Audit Metadata