openspec-archiving

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various shell commands such as mkdir, mv, sed, cat, and git to manage files within the local project directory structure (specifically the spec/ directory). These are standard operations for a documentation archiving tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external markdown content.
  • Ingestion points: The skill reads specification delta files located in spec/changes/{change-id}/specs/**/*.md (found in SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within these markdown files.
  • Capability inventory: The skill has the capability to write to local files (cat >>), modify file content (sed -i), move directories (mv), and perform version control actions (git commit) (found in SKILL.md).
  • Sanitization: No sanitization, validation, or escaping is performed on the content of the markdown files before they are merged into the living documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:04 PM
Security Audit — agent-trust-hub — openspec-archiving