prompt-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external prompts, which introduces a vulnerability surface where instructions embedded in those prompts could influence agent behavior. Ingestion points: user-provided prompts and LLM requirements; Boundary markers: not explicitly defined; Capability inventory: no tools or scripts are defined in this skill; Sanitization: the instructions specifically mention that safety filters must be enabled properly.
- [NO_CODE]: The skill consists entirely of natural language instructions and does not include any executable scripts, binaries, tool configurations, or external dependencies.
Audit Metadata