travel-operations
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection. During Phase 1 (Operations System Discovery), it scans local project files and accepts user input via $ARGUMENTS to identify infrastructure like GDS connectivity and Departure Control Systems. This ingested content is then processed to generate a comprehensive analysis report in docs/travel-operations-analysis.md. The instructions lack explicit boundary markers or directives to the agent to ignore embedded instructions within the discovered data, creating a risk where malicious files in the scanned environment could influence the agent's output or actions.
- Ingestion points: System discovery phase (Phase 1) and user-provided $ARGUMENTS (SKILL.md).
- Boundary markers: Absent; the skill does not wrap external data in delimiters or provide 'ignore instructions' warnings.
- Capability inventory: The skill performs file writing to docs/travel-operations-analysis.md and appends telemetry to ~/.claude/projects/skill-telemetry.md (SKILL.md).
- Sanitization: Absent; there is no evidence of validation or filtering for data processed from the filesystem.
Audit Metadata