pm-career-coach

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied career information to create and save documents, creating a potential surface for indirect instructions.\n
  • Ingestion points: User responses to career stage and goal questions via AskUserQuestion (Steps 1 and 2).\n
  • Boundary markers: Absent; user input is not delimited from system instructions during the plan generation phase.\n
  • Capability inventory: Bash is used for static directory creation and Write is used for file output in SKILL.md.\n
  • Sanitization: No explicit filtering or sanitization of user-provided strings is mentioned before writing to the plan file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 01:16 PM