hugo-to-markdown
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a local Hugo repository, including content files, configuration (
hugo.toml), archetypes, and data sources. This constitutes a surface for indirect prompt injection where malicious instructions embedded in the source repository could attempt to influence the agent's behavior. - Ingestion points: Data enters the agent's context through the reading of
hugo.toml, site configuration files, content files (content/**), archetypes, and thedata/directory. - Boundary markers (absent): The instructions do not specify the use of delimiters or boundary markers to isolate processed repository content from the agent's core instructions.
- Capability inventory: The skill utilizes bundled Python scripts (
scripts/inventory_hugo_rules.pyandscripts/check_standard_markdown.py), performs extensive local file reads, and writes converted Markdown to an output directory. - Sanitization (absent): While the skill performs structural conversion and metadata normalization, it does not implement specific sanitization or filtering to neutralize potentially malicious instructions embedded within the source content or configuration fields.
Audit Metadata