proj-resume
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external files, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill reads content from
docs/task/directory, specifically files matching the*_任务.mdpattern (Step 1). - Boundary markers: There are no instructions to use delimiters or ignore embedded natural language instructions within the task documents. The skill explicitly treats these files as the "sole source of truth."
- Capability inventory: The skill's stated purpose is to "continue development," which in an agentic context typically implies the ability to write files, modify code, or execute shell commands through the agent's core toolset.
- Sanitization: There is no evidence of validation, escaping, or filtering of the content extracted from the task documents before it influences the agent's next steps.
Audit Metadata