ci-cd-and-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a feedback loop where users are instructed to paste raw CI failure output directly into the agent's prompt to facilitate automated fixes. This creates a vulnerability surface for indirect prompt injection if an attacker can control the output of a test, lint, or build process (e.g., via a compromised dependency or malicious pull request) to include instructions that the agent might inadvertently execute.
- Ingestion points: Raw CI failure logs pasted into the prompt as described in the "Feeding CI Failures Back to Agents" section of SKILL.md.
- Boundary markers: Absent; the instructions do not suggest wrapping the logs in delimiters (like XML tags or triple backticks) or providing instructions to the agent to treat the logs as data only.
- Capability inventory: The skill encourages the agent to execute shell commands (e.g.,
npm run lint --fix) and perform file-system modifications based on the error output. - Sanitization: Absent; there is no guidance on sanitizing or filtering the log content before it is processed by the agent.
Audit Metadata