kb-ingest
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (
scan_ingest_delta.py,sync_source_manifest.py) located in a relative path (../obsidian-notes-karpathy/scripts/). This assumes the presence of these scripts in the local environment and expands the skill's execution scope beyond its own directory. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted raw data.
- Ingestion points: Reads files from
raw/**andCLAUDE.mdto populateraw/_manifest.yaml. - Boundary markers: Absent. There are no instructions to the agent to disregard potential commands or instructions embedded within the raw source files.
- Capability inventory: The skill can execute local Python scripts and perform file write operations (
raw/_manifest.yaml). - Sanitization: Absent. No evidence of content validation or escaping is present before the data is processed or added to the manifest.
Audit Metadata