handoff
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the
mktemputility to generate a temporary file path for the handoff document. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from the current conversation history and external artifacts like PRDs, ADRs, and issues.
- Ingestion points: Conversation history and artifact files (referenced by path or URL) defined in SKILL.md.
- Boundary markers: None; the skill does not use delimiters or instructions to ignore embedded commands in the source material.
- Capability inventory: File system read/write operations and shell command execution (
mktemp). - Sanitization: None; the skill does not validate or escape the content of the summarized conversation or artifacts before writing them to disk.
Audit Metadata