developer-journey-map
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the ingestion of external, untrusted data to function, specifically support tickets, community questions, and issue reports (documented in Step 2). This data ingestion surface is susceptible to indirect prompt injection if an attacker embeds malicious instructions in the content being analyzed.
- Ingestion points: Support tickets, GitHub issues, and community thread content processed during evidence collection (SKILL.md, references/evidence-and-signals.md).
- Boundary markers: Absent. There are no instructions for the agent to use delimiters or ignore embedded instructions within the ingested data.
- Capability inventory: The skill uses file-writing capabilities to maintain a project context file (devrel-context.md) and presents analysis to the user. No high-risk capabilities like subprocess execution or network exfiltration were detected.
- Sanitization: Absent. The skill does not instruct the agent to sanitize or validate the external content prior to analysis.
Audit Metadata