skills/waynesutton/markdown-site/dev/Gen Agent Trust Hub

dev

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the command git log --date=short -n 10 to retrieve repository history, which is a standard procedure for maintaining project changelogs.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing content from external project files.* Ingestion points: Reads from files.md, changelog.md, task.md, and documents within the prds/ folder.* Boundary markers: None. There are no instructions provided to distinguish between system instructions and content from these files.* Capability inventory: The skill has the capability to write to the file system and execute shell commands via Git.* Sanitization: None. The skill does not specify any validation or sanitization steps for the data retrieved from the workspace files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 02:25 PM
Security Audit — agent-trust-hub — dev