postmortem

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates a structured reflection process by reading upstream project documentation files and writing a new artifact (docs/ai-native/13-postmortem.md). All operations are confined to the local project directory.
  • [PROMPT_INJECTION]: The skill processes user-supplied notes and reads existing documentation to generate its report. This represents a surface for indirect prompt injection; however, because the skill lacks network access, command execution, or administrative capabilities, the risk is minimal and consistent with its intended use.
  • Ingestion points: Processes user input (AI usage notes, test results) and reads multiple files from the docs/ai-native/ directory as described in the 'Source Loading Protocol' in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are used to wrap external content.
  • Capability inventory: File read and write operations restricted to the local filesystem.
  • Sanitization: No explicit sanitization or validation is performed on the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 04:18 AM
Security Audit — agent-trust-hub — postmortem