free-tool-strategy
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides business strategy and evaluation frameworks. No malicious patterns, obfuscation, or dangerous command executions were detected.- [NO_CODE]: The skill is composed entirely of markdown instructions and configuration data. It does not include any executable scripts (e.g., Python, JavaScript) or binaries, which significantly reduces the potential for technical exploitation.- [PROMPT_INJECTION]: The skill contains a directive to read local context files (such as
.agents/product-marketing-context.md). This constitutes an indirect prompt injection surface as it ingests data that could be influenced by a repository contributor. - Ingestion points:
SKILL.md(Initial Assessment section). - Boundary markers: Not present in the instructions.
- Capability inventory: The skill does not request or use any tools for file writing, network access, or subprocess execution.
- Sanitization: No content filtering is specified. The risk is assessed as safe because the agent lacks the necessary tools to perform harmful actions based on injected instructions.
Audit Metadata