deep-research-partnership-planner
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell scripts during Phase 5 (Consolidation & Final Briefing) to merge multiple generated Markdown files into a single unified archive document.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of Deep Research reports provided by the user during Phase 2 and Phase 3.
- Ingestion points: External research reports are ingested into the agent context in Phase 2/3 from the
SKILL.mdworkflow. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the skill's instructions.
- Capability inventory: The skill possesses file writing capabilities (Phase 4) and shell command execution (Phase 5) within
SKILL.md. - Sanitization: There are no explicit instructions for sanitizing or validating the content of the external research reports before they are used to generate plans or executed upon in scripts.
Audit Metadata