context-layer-consolidation
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local scripts
scripts/lint --reportandscripts/lintas part of its operational workflow for maintaining the wiki. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The agent reads markdown content from several directories, including
org/,areas/, anddecisions/, as well as existing Space pages. - Boundary markers: The instructions do not provide delimiters or specific warnings to ignore instructions that might be embedded within the processed markdown files.
- Capability inventory: The skill grants the agent authority to modify markdown files and execute local scripts within the project repository.
- Sanitization: No sanitization or validation procedures are defined for the data read from the external markdown files before processing.
Audit Metadata