pickup
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection vulnerability surface. It processes handoff cards from the local file system and instructs the agent to use their contents as its primary work instructions, which could allow a malicious file to hijack the session's behavior.
- Ingestion points: The skill reads all content from markdown files located in the
.claude/handoffs/directory (SKILL.md). - Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to help the agent distinguish between the skill's instructions and potentially malicious content within the handoff files.
- Capability inventory: The skill uses shell commands (
grep) to locate files and file editing tools to modify their status (SKILL.md). - Sanitization: Absent. There is no validation, filtering, or escaping applied to the content of the handoff files before the agent processes them.
Audit Metadata