code-walkthrough
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
showboat execto run shell utilities such assed,grep,cat, andheadto extract code snippets and capture live output for documentation purposes. - [EXTERNAL_DOWNLOADS]: Recommends installing the
showboatutility via standard package managers (pip,uv,go) from the official repository of a well-known developer (simonw/showboat). - [INDIRECT_PROMPT_INJECTION]: As the skill reads and processes local source code to generate narrative documentation, it is susceptible to instructions embedded within that code. Evidence: (1) Ingestion points: Reads local files via shell commands in
SKILL.md. (2) Boundary markers: No delimiters or ignore instructions are specified. (3) Capability inventory: Executes shell commands and scripts viashowboat exec. (4) Sanitization: No sanitization or validation of the extracted code content is performed.
Audit Metadata