gitsite-content-manager

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a local Python script scripts/manage_content.py designed to automate file system operations like directory creation and content deletion.
  • [INDIRECT_PROMPT_INJECTION]: The script ingests user-provided text (e.g., titles, descriptions) and interpolates it into Markdown files and the site.yml configuration.
  • Ingestion points: CLI arguments passed to manage_content.py (e.g., --title, --description).
  • Boundary markers: Markdown headers and YAML structures are used to encapsulate input in the generated files.
  • Capability inventory: The script uses pathlib for file/directory creation and shutil.rmtree for content deletion within the scripts/manage_content.py file.
  • Sanitization: While a _slugify function is used for directory names, input interpolated into the site.yml navigation list is not fully escaped, which could lead to malformed YAML if malicious characters are injected.
  • [METADATA_POISONING]: The SKILL.md documentation claims the tool generates complete YAML frontmatter, but the implementation in scripts/manage_content.py explicitly omits it and states that the platform does not support it. This inconsistency between the skill's stated capabilities and its actual behavior could mislead users or agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 12:51 PM