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.ndjsonand 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
gitand run theregistry-events.pyscript usingpython3for 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-toplevelfor path resolution andpython3 "$AARON_SKILLS_ROOT/scripts/registry-events.py"for ledger mutations.
Audit Metadata