release-rollout
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to read an external file named
SKILL.local.mdif it exists and apply the instructions contained within. This creates an indirect prompt injection surface where untrusted content from the local file system could influence the agent's behavior during the rollout process. - Ingestion points: The file
SKILL.local.mdis read at the start of the session. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the contents of the local file as potentially untrusted or to ignore embedded commands.
- Capability inventory: The skill primarily guides the user through git operations and manual pipeline triggers. It also mentions using the
oncall-shiftskill to post updates to JIRA. - Sanitization: There is no evidence of sanitization or validation of the instructions loaded from the local override file.
Audit Metadata