aporia-sync
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as code diffs and pull request metadata, which could be used to deliver malicious instructions to the agent.
- Ingestion points: Untrusted data enters the agent context through
git diffandgh pr view(capturing PR titles, bodies, and comments) as specified inSKILL.md. - Boundary markers: The skill instructions do not require the use of boundary markers or explicit warnings to ignore instructions embedded within the processed data.
- Capability inventory: The agent possesses significant write capabilities via the
aporia:apply_scan,aporia:record_notes, andaporia:resolve_itemstools, which can modify the product map and resolve inbox items. - Sanitization: There is no mention of sanitization, filtering, or validation of the ingested data before it is interpolated into prompts or stored in the Aporia system.
Audit Metadata