afk-resume-workflow
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized exfiltration attempts were detected in the skill instructions or configuration.
- [PROMPT_INJECTION]: The skill reads external data from the repository (specifically from the
docs/directory and tracking files) to influence its decision-making. This ingestion of untrusted data represents an indirect prompt injection surface where files could contain instructions designed to redirect the agent's behavior. - Ingestion points:
SKILL.md(readingdocs/<task-slug>/tracking/packets, handoff notes, and spec files). - Boundary markers: None identified; instructions do not explicitly tell the agent to ignore instructions embedded in the tracking data.
- Capability inventory: The skill primarily routes to other internal skills and reports status; no shell execution or network capabilities are present in this specific skill definition.
- Sanitization: No validation or filtering of the content read from the repository is specified.
Audit Metadata