media-to-roadmap
Fail
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill instructions direct the agent to access and inventory local system configuration files, including ~/.claude/settings.json, ~/.claude/skills/, and ~/.claude/CLAUDE.md. These files typically contain sensitive agent settings, API tokens, or internal security rules.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its design of fetching and processing untrusted content from external sources such as YouTube transcripts and social media threads. 1. Ingestion points: External URLs are retrieved via ctx_fetch_and_index and ctx_execute tools. 2. Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded instructions within the fetched data. 3. Capability inventory: The agent has the ability to read system-level configuration files and write new files to the local directory. 4. Sanitization: There is no requirement for input validation or sanitization of the retrieved external content.
Recommendations
- AI detected serious security threats
Audit Metadata