The Agent Skills Directory

[SAFE]: The skill operates within its intended scope, managing contract-related information in a dedicated configuration directory. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. The file access is restricted to the plugin's own configuration state path.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and displays contract data from external sources, though no active exploit was detected.
Ingestion points: Data is read from ~/.claude/plugins/config/claude-for-legal/commercial-legal/renewal-register.yaml and scanned from external Contract Management Systems (CLM) and e-signature tools.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts when displaying contract notes or metadata.
Capability inventory: The skill has file read/write access to its specific configuration directory and can query integrated contract management tools.
Sanitization: No explicit sanitization or validation of imported contract fields is mentioned in the logic.

renewal-tracker