file-categorization
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze and categorize external, potentially untrusted file content.
- Ingestion points: The categorization logic accepts file
contentas input (referenced in thecategorizeFilepseudo-code) to perform frontmatter and structural analysis. - Boundary markers: The skill relies on detecting standard markdown headers (e.g.,
## When to Use,## Agent Identity) but does not implement explicit boundary markers or instructions to the agent to ignore embedded commands within the files being processed. - Capability inventory: While the skill itself is an analyzer, it is explicitly designed to be used by commands like
/integration-processand/integration-validateto determine target directories and trigger automated processing of files marked with 'High' confidence. - Sanitization: There is no evidence of sanitization or filtering of the external content before it is processed by the categorization algorithm, creating a surface where malicious content could attempt to manipulate the classification verdict.
Audit Metadata