handoff
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted conversation history and user-supplied arguments to generate a summary, creating a surface for indirect prompt injection. Ingestion points: The 'current conversation' and user-provided arguments processed in
SKILL.md. Boundary markers: No explicit delimiters or instructions are provided to separate the summary task from potential commands in the history. Capability inventory: The skill instructs the agent to write files to the system's temporary directory. Sanitization: The skill mandates redacting sensitive credentials but lacks sanitization for executable instructions within the conversation history. - [COMMAND_EXECUTION]: The skill requires the agent to resolve system environment variables to determine file paths. Evidence: Reference to
$TMPDIR,/tmp, and%TEMP%inSKILL.md.
Audit Metadata