alan-plan
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, untrusted data to generate plans, which creates a surface for indirect prompt injection.
- Ingestion points: Instructions in
SKILL.mddirect the agent to ingest data from task descriptions, linked context, codebase exploration, and existing artifacts viamcp__alan__get_artifact. - Boundary markers: There are no instructions in
SKILL.mdregarding the use of delimiters or directives to ignore instructions embedded in the ingested data. - Capability inventory: The agent is authorized in
SKILL.mdto persist and modify content usingmcp__alan__create_plan,mcp__alan__update_artifact, andmcp__alan__add_artifact_comment. - Sanitization: No procedures for sanitizing or validating external content are defined in
SKILL.md.
Audit Metadata