project-landscape
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a significant surface for indirect prompt injection by explicitly directing the agent to discover and obey instructions from external project files.
- Ingestion points: The agent is instructed to read
AGENTS.md,CLAUDE.md,README.md, and any skill files located in~/Developer/<repo>/.cursor/skills/or~/Developer/<repo>/.claude/skills/. - Boundary markers: No delimiters or instructions are provided to help the agent distinguish between its own system instructions and potentially malicious commands embedded in these external files.
- Capability inventory: The agent has extensive file system access (absolute path reads, Grep, Glob) and the ability to launch subagents, which could be exploited if an ingested file contains malicious instructions.
- Sanitization: There is no requirement for the agent to validate or sanitize the content of these discovered files before treating them as authoritative instructions.
Audit Metadata