session-info

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local TypeScript script using the bun runtime. The script path is located within the user's home directory at $HOME/.claude/plugins/marketplaces/cc-skills/plugins/statusline-tools/scripts/get-session-info.ts, which is consistent with the skill's stated purpose of providing session information.
  • [PROMPT_INJECTION]: The skill processes data from the session registry, creating a surface for indirect prompt injection from session history.
  • Ingestion points: Reads session history and metadata from ~/.claude/projects/{encoded-path}/.session-chain-cache.json.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded content are defined in the skill documentation.
  • Capability inventory: The skill has Bash (to execute the script via bun) and Read (to access the registry file) permissions.
  • Sanitization: No evidence of sanitization or validation is described for the content retrieved from the session registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 03:53 AM