skills/jcosta33/skills/sus-spec/Gen Agent Trust Hub

sus-spec

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes content from external sources (like issue trackers) that may contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The skill reads project rules, current code, durable decisions, related artifacts, and open issues during the context-gathering phase (SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or to disregard instructions found within the ingested data.
  • Capability inventory: The skill allows the agent to read project files, write artifacts to ~/.agents/artifacts/, and delete files during the 'Close' phase (SKILL.md).
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from external project files or issues.
  • [DATA_EXFILTRATION]: The skill performs broad file system operations, including reading project source code and managing files in a hidden directory within the user's home folder.
  • Evidence: The workflow requires reading 'current code' and 'related artifacts' and resolving the absolute path ~/.agents/artifacts/<workspace>/ for writing and eventual deletion of files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 07:26 PM
Security Audit — agent-trust-hub — sus-spec