do-show-me
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to interact with locally generated artifacts.
- Evidence:
SKILL.mdcontains instructions to runplannotator annotate <path> --gate --jsonoropen path/to/show-me-{description}.htmldepending on the environment configuration. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface where untrusted user input (the topic or description) is used to generate HTML files that are subsequently processed by shell-level commands.
- Ingestion points: User-provided conversation topics and descriptions used for file naming (
SKILL.md). - Boundary markers: Absent; there are no instructions to the agent to sanitize or delimit the user-provided data.
- Capability inventory: Shell command execution (
open,plannotator) and file system interaction (creating HTML files). - Sanitization: Absent; the skill does not specify how to handle potentially malicious characters in the
{description}variable used in shell paths.
Audit Metadata