skills/hashintel/labs/assumptions/Gen Agent Trust Hub

assumptions

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from external sources.
  • Ingestion points: The skill reads project-related artifacts such as 'cards', 'spike verdicts', and 'slice summaries' to extract specific lines.
  • Boundary markers: There are no explicit instructions or delimiters to isolate processed data from the agent's core instructions, nor are there directives to ignore embedded instructions within the processed content.
  • Capability inventory: The skill has the capability to read from and write to the local file system (specifically the docs/ directory).
  • Sanitization: The skill does not define any escaping, filtering, or validation logic for the extracted content before it is interpolated into the prompt or written to the ledger file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:31 AM
Security Audit — agent-trust-hub — assumptions