cross-campaign
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates discovery and ingestion of content from various external projects (camps), creating a surface for indirect prompt injection where untrusted data could influence agent behavior.
- Ingestion points: File reading from external paths via cat or camp transfer.
- Boundary markers: No explicit delimiters or instructions to ignore embedded content.
- Capability inventory: File system read/write access and execution of the camp CLI utility.
- Sanitization: No sanitization of ingested content is specified.
- [COMMAND_EXECUTION]: The skill relies on executing shell commands (camp, cat, jq) to manage projects and read data. These commands are part of the core project management functionality and do not exhibit signs of misuse or privilege escalation.
Audit Metadata