alt-text
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown instructions and does not contain any executable scripts, binaries, or software packages.\n- [PROMPT_INJECTION]: The skill accepts user-provided text context (details about a post), creating a surface for indirect prompt injection.\n
- Ingestion points: User input describing the post or blogpost (SKILL.md task section).\n
- Boundary markers: None present; user context is interpolated without delimiters or instructions to ignore embedded commands.\n
- Capability inventory: The agent has no access to the file system, network resources, or command execution tools.\n
- Sanitization: No explicit input validation or sanitization is performed on the user-provided text.
Audit Metadata