agile-retro
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from potentially untrusted external sources such as user/stakeholder feedback and various project reports.
- Ingestion points: Processes content from 'Status closure reports', 'Status checkpoints', 'Sprint review', 'Sprint metrics', and 'User or stakeholder feedback' as specified in
SKILL.md. - Boundary markers: The instructions do not mandate the use of delimiters or specific 'ignore instructions' markers when handling these external data inputs.
- Capability inventory: The agent is granted capabilities to read files (to gather context) and write files (to save the retrospective artifact to paths like
planning/retros/). - Sanitization: No specific sanitization or filtering steps are defined for the content extracted from external reports before it is presented to the model.
Audit Metadata