accint-commitments
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data originating from the output of the
acc commitmentscommand to triage and close promises. - Ingestion points: Data enters the agent's context through the output of the
acc commitmentsCLI command (SKILL.md). - Capability inventory: The skill utilizes the
acc_acttool to modify the state of commitments based on processed data. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the triaging logic and potentially malicious instructions embedded within the commitment text.
- Sanitization: No filtering or sanitization steps are defined for the input retrieved from the external command.
Audit Metadata