paper-cuts
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon potentially untrusted data from external sources during its reporting and research phase.
- Ingestion points: The agent is instructed to read command outputs, error messages, version information from lockfiles, and content from external issue trackers or documentation sites.
- Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the content extracted from error messages or external research when drafting the "Paper cuts" report.
- Capability inventory: The skill utilizes file-reading capabilities for local configuration and lockfiles, network-based search tools for researching upstream issues, and potentially network or file-write capabilities for opening issues or applying fixes.
- Sanitization: The instructions do not specify sanitization or escaping protocols for external content before it is processed or interpolated into the final report.
Audit Metadata