marketing-kuaishou-strategist
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an execution path for user-supplied tasks without implementing defensive measures to prevent instruction overrides or data poisoning.
- Ingestion points: User tasks are ingested via command-line arguments or standard input through the
scripts/run.shscript. - Boundary markers: There are no explicit delimiters or instructions within
SKILL.mdto isolate system instructions from the content of user-provided tasks. - Capability inventory: The skill does not define access to sensitive tools, network operations, or file-writing capabilities in its frontmatter or associated scripts.
- Sanitization: No validation, filtering, or escaping of input data is performed before the agent processes the task.
Audit Metadata