offer-claims-registry

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user-provided marketing claims and offers, which creates an attack surface for indirect prompt injection.
  • Ingestion points: Reads memory/events/claims.ndjson and user-attested facts provided during registry updates in the SKILL.md instructions.
  • Boundary markers: The skill uses [needs source] markers for unresolved evidence and instructs the agent to treat drafts as untrusted evidence.
  • Capability inventory: Can execute shell commands via git and run the registry-events.py script using python3 for file writes.
  • Sanitization: Instructions mandate verifying the registry script, event schema, and system catalog before any invocation.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform environment path resolution and execute a script to update the claims ledger.
  • Evidence: Commands include git rev-parse --show-toplevel for path resolution and python3 "$AARON_SKILLS_ROOT/scripts/registry-events.py" for ledger mutations.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 07:29 PM
Security Audit — agent-trust-hub — offer-claims-registry