skills/jeremylongshore/tons-of-skills-marketplace/grammarly-data-safety-guardian/Gen Agent Trust Hub
grammarly-data-safety-guardian
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of a Grammarly submission manifest, creating a surface for indirect prompt injection attacks where malicious instructions could be embedded in metadata fields.
- Ingestion points: The
submission-manifest.jsonfile (described inreferences/submission-contract.md) is ingested and passed to theaudit_submission_manifest.pyscript via stdin. - Boundary markers: The skill relies on the script's deterministic JSON output but does not explicitly instruct the agent to ignore potentially malicious instructions embedded within the manifest data itself.
- Capability inventory: The skill is authorized to use
Bash(python3:*)to execute its local audit script. The script is explicitly designed to be offline and does not perform network operations, filesystem writes, or process raw document content. - Sanitization: The
audit_submission_manifest.pyscript implements rigorous validation, including strict JSON parsing (blocking duplicate keys and non-standard constants viaobject_pairs_hook), field validation against allowed value sets (e.g.,OPERATIONS,CLASSIFICATIONS), and recursive regex-based scanning (scan_unsafe) for secrets (e.g., private keys, API tokens) and forbidden content-related keywords (e.g.,raw_text,credential).
Audit Metadata