problem-statement
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted user text (persona descriptions and struggle details) and interpolates them into its output framing without sufficient protection.
- Ingestion points: Input context provided during invocation, including the argument-hint and pasted context dumps as identified in the Input section of SKILL.md.
- Boundary markers: The skill instructions do not utilize delimiters or specific directives to the model to ignore potential instructions embedded within the user-provided context.
- Capability inventory: The skill is restricted to text generation; it requests no tools in its YAML frontmatter and performs no network or file system operations.
- Sanitization: No input validation or filtering is applied to the user-supplied data.
- [NO_CODE]: The skill consists entirely of Markdown instructions, templates, and examples; it does not include any executable scripts, binaries, or automated shell commands.
Audit Metadata