Skills
Navigate
skills/vishalsachdev/claude-code-skills/premortem/Gen Agent Trust Hub

premortem

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local workspace to gather context for the premortem analysis.
  • Ingestion points: Step 1 uses Glob and Read tools to scan CLAUDE.md, memory/ folders, and user-referenced project briefs.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these files.
  • Capability inventory: The skill uses Write to create files, Bash to execute commands (timestamping and opening reports), and Agent to spawn sub-tasks.
  • Sanitization: There is no mention of sanitizing or filtering the content gathered from workspace files before it is interpolated into sub-agent prompts or the final HTML report.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool in Step 6 to generate timestamps using date and to open the generated report using open (macOS) or xdg-open (Linux). While these are standard reporting behaviors, they involve executing shell commands based on the skill's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 06:09 PM