project-fingerprinting
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a bash script to execute several system commands for metadata collection.
- Evidence: The 'Quick Commands for Fingerprinting' section in
SKILL.mdincludescat,ls,git log,find, andwcto inspect the file system and project history. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of reading external, potentially untrusted project files.
- Ingestion points: The skill reads contents from
package.json,tsconfig.json, and directory structures (SKILL.md). - Boundary markers: Absent. The output of file reads is directly concatenated into the agent's context without clear delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill has the capability to execute shell commands (
ls,cat,git,find) as seen in the 'Quick Commands' section ofSKILL.md. - Sanitization: No sanitization or validation of the file content is performed before the data is passed to other specialist agents.
Audit Metadata