pickup
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of a Markdown file providing instructions to the AI on how to format a summary. There are no associated scripts (.sh, .py, .js) or executables.
- [DATA_EXFILTRATION] (SAFE): There are no network operations (curl, wget, etc.) or hardcoded credentials. The skill only prompts the user to copy-paste text.
- [INDIRECT_PROMPT_INJECTION] (SAFE): The skill processes conversation history (untrusted input).
- Ingestion points: The AI processes its own conversation history to generate the summary.
- Boundary markers: The output is wrapped in fenced code blocks to distinguish it from instructions.
- Capability inventory: The skill has no capabilities (no file writing, no shell execution, no network access).
- Sanitization: None required as the output is static text with no functional side effects.
- [PRIVILEGE_ESCALATION] (SAFE): No commands are executed, and no system settings are modified.
Audit Metadata