explain
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
head,grep,ls, andcatto inspect local project files. These commands are used to retrieve context (imports, function bodies, directory structures) required to generate accurate explanations. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external files, creating a surface for indirect prompt injection.
- Ingestion points: Files specified in the
$FILEargument or discovered via directory listing in$DIR(e.g., inSKILL.md). - Boundary markers: Absent. The skill does not define specific delimiters or instructions for the agent to disregard potential prompt injections within the source code being analyzed.
- Capability inventory: The skill uses shell commands (
head,grep,ls,cat) to read files but does not appear to perform network operations or persistent system changes. - Sanitization: No sanitization or validation of the file content is performed before the agent processes it for explanation.
Audit Metadata