jira-standup-auditor
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill correlates and summarizes data from external sources, specifically Jira Cloud issue summaries and changelogs, and local Git repository telemetry (commit messages, branch names, and staged file paths). These sources are controlled by third parties and could contain malicious instructions designed to manipulate the agent's output or behavior.
- Ingestion points: Data enters the agent's context through the output of
scripts/get-recent-jira-activity.sh(Jira API) andscripts/get-local-git-activity.sh(Git history). - Boundary markers: The instructions in
SKILL.mddo not specify the use of delimiters or explicit directives to ignore instructions embedded within the retrieved data. - Capability inventory: The agent can execute provided shell scripts and read local files. While the skill's scripts are constrained, the agent's runtime environment may possess broader system access that could be targeted by an injection.
- Sanitization: The skill does not perform content sanitization or filtering on the ticket summaries or commit messages before presenting them to the LLM for summarization.
Audit Metadata